Geekbench ML Score

709
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date July 16 2022 03:27 PM
Views 1

System Information

System Information
Operating System iOS 15.5
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% 491
52.6 IPS
 
Image Classification (F16)
100% 483
51.8 IPS
 
Image Classification (I8)
81% 797
85.4 IPS
 
Image Segmentation (F32)
100% 595
3.68 IPS
 
Image Segmentation (F16)
100% 582
3.59 IPS
 
Image Segmentation (I8)
89% 1384
8.55 IPS
 
Pose Estimation (F32)
100% 246
0.99 IPS
 
Pose Estimation (F16)
100% 324
1.31 IPS
 
Pose Estimation (I8)
80% 385
1.56 IPS
 
Object Detection (F32)
100% 765
26.9 IPS
 
Object Detection (F16)
100% 758
26.6 IPS
 
Object Detection (I8)
52% 1105
38.8 IPS
 
Face Detection (F32)
100% 875
10.1 IPS
 
Face Detection (F16)
100% 876
10.1 IPS
 
Face Detection (I8)
75% 1153
13.3 IPS
 
Text Classification (F32)
100% 1047
414.1 IPS
 
Text Classification (F16)
100% 1075
425.3 IPS
 
Machine Translation (F32)
100% 907
139.8 IPS
 
Machine Translation (F16)
100% 912
140.5 IPS
 

Compare

Set Baseline