Geekbench ML Score

921
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 06 2022 01:56 AM
Views 1

System Information

System Information
Operating System iOS 16.0
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% 789
84.5 IPS
 
Image Classification (F16)
100% 751
80.5 IPS
 
Image Classification (I8)
81% 466
49.9 IPS
 
Image Segmentation (F32)
100% 1116
6.89 IPS
 
Image Segmentation (F16)
100% 1082
6.69 IPS
 
Image Segmentation (I8)
89% 1463
9.04 IPS
 
Pose Estimation (F32)
100% 418
1.69 IPS
 
Pose Estimation (F16)
100% 408
1.65 IPS
 
Pose Estimation (I8)
80% 476
1.92 IPS
 
Object Detection (F32)
100% 1051
36.9 IPS
 
Object Detection (F16)
100% 1057
37.1 IPS
 
Object Detection (I8)
52% 769
27.0 IPS
 
Face Detection (F32)
100% 1320
15.2 IPS
 
Face Detection (F16)
100% 1288
14.8 IPS
 
Face Detection (I8)
75% 845
9.71 IPS
 
Text Classification (F32)
100% 970
383.6 IPS
 
Text Classification (F16)
100% 1072
424.1 IPS
 
Machine Translation (F32)
100% 2043
314.9 IPS
 
Machine Translation (F16)
100% 2030
312.9 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download