Geekbench ML Score

905
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 05:03 AM
Views 1

System Information

System Information
Operating System iOS 16.1.2
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% 784
84.0 IPS
 
Image Classification (F16)
100% 738
79.1 IPS
 
Image Classification (I8)
81% 471
50.4 IPS
 
Image Segmentation (F32)
100% 1084
6.70 IPS
 
Image Segmentation (F16)
100% 1042
6.44 IPS
 
Image Segmentation (I8)
89% 1425
8.80 IPS
 
Pose Estimation (F32)
100% 409
1.66 IPS
 
Pose Estimation (F16)
100% 401
1.62 IPS
 
Pose Estimation (I8)
80% 467
1.89 IPS
 
Object Detection (F32)
100% 1010
35.5 IPS
 
Object Detection (F16)
100% 1003
35.2 IPS
 
Object Detection (I8)
52% 778
27.3 IPS
 
Face Detection (F32)
100% 1283
14.7 IPS
 
Face Detection (F16)
100% 1236
14.2 IPS
 
Face Detection (I8)
75% 852
9.79 IPS
 
Text Classification (F32)
100% 1001
396.1 IPS
 
Text Classification (F16)
100% 1016
401.7 IPS
 
Machine Translation (F32)
100% 2048
315.7 IPS
 
Machine Translation (F16)
100% 2045
315.1 IPS
 

Compare

Set Baseline