Geekbench ML Score

744
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 14 2022 11:16 PM
Views 1

System Information

System Information
Operating System iOS 15.2.1
Model iPhone 11 Pro
Model IDiPhone12,3
Motherboard D421AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.68 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 549
58.8 IPS
 
Image Classification (F16)
100% 544
58.3 IPS
 
Image Classification (I8)
81% 320
34.2 IPS
 
Image Segmentation (F32)
100% 877
5.42 IPS
 
Image Segmentation (F16)
100% 875
5.41 IPS
 
Image Segmentation (I8)
89% 1114
6.88 IPS
 
Pose Estimation (F32)
100% 286
1.16 IPS
 
Pose Estimation (F16)
100% 283
1.15 IPS
 
Pose Estimation (I8)
80% 341
1.38 IPS
 
Object Detection (F32)
100% 804
28.2 IPS
 
Object Detection (F16)
100% 814
28.6 IPS
 
Object Detection (I8)
52% 609
21.4 IPS
 
Face Detection (F32)
100% 1005
11.5 IPS
 
Face Detection (F16)
100% 999
11.5 IPS
 
Face Detection (I8)
75% 716
8.23 IPS
 
Text Classification (F32)
100% 2000
790.9 IPS
 
Text Classification (F16)
100% 1990
787.0 IPS
 
Machine Translation (F32)
100% 1204
185.5 IPS
 
Machine Translation (F16)
100% 1201
185.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download