Geekbench ML Score

729
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 25 2023 10:30 AM
Views 1

System Information

System Information
Operating System iOS 16.2
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% 548
58.8 IPS
 
Image Classification (F16)
100% 542
58.0 IPS
 
Image Classification (I8)
81% 321
34.4 IPS
 
Image Segmentation (F32)
100% 875
5.41 IPS
 
Image Segmentation (F16)
100% 864
5.34 IPS
 
Image Segmentation (I8)
89% 1116
6.89 IPS
 
Pose Estimation (F32)
100% 279
1.13 IPS
 
Pose Estimation (F16)
100% 277
1.12 IPS
 
Pose Estimation (I8)
80% 340
1.37 IPS
 
Object Detection (F32)
100% 802
28.1 IPS
 
Object Detection (F16)
100% 803
28.2 IPS
 
Object Detection (I8)
52% 620
21.8 IPS
 
Face Detection (F32)
100% 1007
11.6 IPS
 
Face Detection (F16)
100% 994
11.4 IPS
 
Face Detection (I8)
75% 725
8.33 IPS
 
Text Classification (F32)
100% 1719
679.8 IPS
 
Text Classification (F16)
100% 1676
663.0 IPS
 
Machine Translation (F32)
100% 1204
185.5 IPS
 
Machine Translation (F16)
100% 1169
180.1 IPS
 

Compare

Set Baseline