Geekbench ML Score

910
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 24 2022 06:25 PM
Views 1

System Information

System Information
Operating System iOS 16.1.1
Model iPhone 13
Model IDiPhone14,5
Motherboard D17AP
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 3.56 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 785
84.2 IPS
 
Image Classification (F16)
100% 755
80.9 IPS
 
Image Classification (I8)
81% 469
50.2 IPS
 
Image Segmentation (F32)
100% 1117
6.90 IPS
 
Image Segmentation (F16)
100% 1070
6.61 IPS
 
Image Segmentation (I8)
89% 1454
8.98 IPS
 
Pose Estimation (F32)
100% 406
1.64 IPS
 
Pose Estimation (F16)
100% 400
1.62 IPS
 
Pose Estimation (I8)
80% 474
1.92 IPS
 
Object Detection (F32)
100% 1025
36.0 IPS
 
Object Detection (F16)
100% 1026
36.0 IPS
 
Object Detection (I8)
52% 774
27.2 IPS
 
Face Detection (F32)
100% 1279
14.7 IPS
 
Face Detection (F16)
100% 1233
14.2 IPS
 
Face Detection (I8)
75% 859
9.87 IPS
 
Text Classification (F32)
100% 940
372.0 IPS
 
Text Classification (F16)
100% 1048
414.6 IPS
 
Machine Translation (F32)
100% 2053
316.4 IPS
 
Machine Translation (F16)
100% 2041
314.6 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download