Geekbench ML Score

714
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 06 2022 03:56 AM
Views 2

System Information

System Information
Operating System iOS 15.6
Model iPhone 11 Pro Max
Model IDiPhone12,5
Motherboard D431AP
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 3.66 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 549
58.9 IPS
 
Image Classification (F16)
100% 515
55.2 IPS
 
Image Classification (I8)
81% 313
33.5 IPS
 
Image Segmentation (F32)
100% 861
5.32 IPS
 
Image Segmentation (F16)
100% 848
5.24 IPS
 
Image Segmentation (I8)
89% 1094
6.76 IPS
 
Pose Estimation (F32)
100% 263
1.06 IPS
 
Pose Estimation (F16)
100% 263
1.06 IPS
 
Pose Estimation (I8)
80% 319
1.29 IPS
 
Object Detection (F32)
100% 776
27.2 IPS
 
Object Detection (F16)
100% 820
28.8 IPS
 
Object Detection (I8)
52% 603
21.2 IPS
 
Face Detection (F32)
100% 955
11.0 IPS
 
Face Detection (F16)
100% 959
11.0 IPS
 
Face Detection (I8)
75% 719
8.26 IPS
 
Text Classification (F32)
100% 1730
684.4 IPS
 
Text Classification (F16)
100% 1684
666.1 IPS
 
Machine Translation (F32)
100% 1205
185.7 IPS
 
Machine Translation (F16)
100% 1203
185.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download