Geekbench ML Score

909
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 29 2023 06:00 PM
Views 1

System Information

System Information
Operating System iOS 17.1.1
Model iPhone 12 Pro
Model IDiPhone13,3
Motherboard D53pAP
CPU Information
Name Apple A14 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.99 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.56 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 701
75.1 IPS
 
Image Classification (F16)
100% 705
75.5 IPS
 
Image Classification (I8)
81% 335
35.9 IPS
 
Image Segmentation (F32)
100% 1068
6.60 IPS
 
Image Segmentation (F16)
100% 1023
6.32 IPS
 
Image Segmentation (I8)
89% 1294
7.99 IPS
 
Pose Estimation (F32)
100% 358
1.45 IPS
 
Pose Estimation (F16)
100% 356
1.44 IPS
 
Pose Estimation (I8)
80% 435
1.76 IPS
 
Object Detection (F32)
100% 1011
35.5 IPS
 
Object Detection (F16)
100% 1025
36.0 IPS
 
Object Detection (I8)
52% 596
20.9 IPS
 
Face Detection (F32)
100% 1232
14.2 IPS
 
Face Detection (F16)
100% 1202
13.8 IPS
 
Face Detection (I8)
75% 789
9.07 IPS
 
Text Classification (F32)
100% 2400
949.3 IPS
 
Text Classification (F16)
100% 2409
952.6 IPS
 
Machine Translation (F32)
100% 1747
269.2 IPS
 
Machine Translation (F16)
100% 1745
269.0 IPS
 

Compare

Set Baseline Geekbench 6 now available