Geekbench ML Score

770
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 06 2021 04:52 AM
Views 1

System Information

System Information
Operating System iOS 15.1
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 3.60 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 404
43.3 IPS
 
Image Classification (F16)
100% 431
46.1 IPS
 
Image Classification (I8)
81% 432
46.2 IPS
 
Image Segmentation (F32)
100% 662
4.09 IPS
 
Image Segmentation (F16)
100% 579
3.58 IPS
 
Image Segmentation (I8)
89% 1363
8.42 IPS
 
Pose Estimation (F32)
100% 297
1.20 IPS
 
Pose Estimation (F16)
100% 320
1.29 IPS
 
Pose Estimation (I8)
80% 434
1.75 IPS
 
Object Detection (F32)
100% 967
33.9 IPS
 
Object Detection (F16)
100% 945
33.2 IPS
 
Object Detection (I8)
52% 812
28.5 IPS
 
Face Detection (F32)
100% 818
9.40 IPS
 
Face Detection (F16)
100% 861
9.89 IPS
 
Face Detection (I8)
75% 875
10.1 IPS
 
Text Classification (F32)
100% 1926
761.9 IPS
 
Text Classification (F16)
100% 1892
748.3 IPS
 
Machine Translation (F32)
100% 1578
243.3 IPS
 
Machine Translation (F16)
100% 1644
253.4 IPS
 

Compare

Set Baseline Geekbench 6 now available