Geekbench ML Score

641
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 22 2021 08:56 PM
Views 1

System Information

System Information
Operating System iOS 15.0.2
Model iPhone 12 Pro
Model IDiPhone13,3
Motherboard D53pAP
CPU Information
Name Apple A14 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.99 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.60 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 410
43.9 IPS
 
Image Classification (F16)
100% 393
42.1 IPS
 
Image Classification (I8)
81% 827
88.6 IPS
 
Image Segmentation (F32)
100% 500
3.09 IPS
 
Image Segmentation (F16)
100% 505
3.12 IPS
 
Image Segmentation (I8)
89% 1296
8.00 IPS
 
Pose Estimation (F32)
100% 242
0.98 IPS
 
Pose Estimation (F16)
100% 299
1.21 IPS
 
Pose Estimation (I8)
80% 360
1.46 IPS
 
Object Detection (F32)
100% 579
20.3 IPS
 
Object Detection (F16)
100% 581
20.4 IPS
 
Object Detection (I8)
52% 940
33.0 IPS
 
Face Detection (F32)
100% 734
8.44 IPS
 
Face Detection (F16)
100% 735
8.45 IPS
 
Face Detection (I8)
75% 954
11.0 IPS
 
Text Classification (F32)
100% 1294
511.9 IPS
 
Text Classification (F16)
100% 1312
518.9 IPS
 
Machine Translation (F32)
100% 834
128.6 IPS
 
Machine Translation (F16)
100% 829
127.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download