Geekbench ML Score

944
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 15 2022 01:28 AM
Views 1

System Information

System Information
Operating System iOS 15.1
Model iPhone 13 Pro
Model IDiPhone14,2
Motherboard D63AP
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 5.56 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 801
85.8 IPS
 
Image Classification (F16)
100% 762
81.6 IPS
 
Image Classification (I8)
81% 458
49.1 IPS
 
Image Segmentation (F32)
100% 1131
6.99 IPS
 
Image Segmentation (F16)
100% 1117
6.90 IPS
 
Image Segmentation (I8)
89% 1461
9.02 IPS
 
Pose Estimation (F32)
100% 428
1.73 IPS
 
Pose Estimation (F16)
100% 421
1.70 IPS
 
Pose Estimation (I8)
80% 491
1.99 IPS
 
Object Detection (F32)
100% 1107
38.8 IPS
 
Object Detection (F16)
100% 1111
39.0 IPS
 
Object Detection (I8)
52% 773
27.1 IPS
 
Face Detection (F32)
100% 1342
15.4 IPS
 
Face Detection (F16)
100% 1313
15.1 IPS
 
Face Detection (I8)
75% 855
9.82 IPS
 
Text Classification (F32)
100% 1135
449.0 IPS
 
Text Classification (F16)
100% 1197
473.3 IPS
 
Machine Translation (F32)
100% 1949
300.4 IPS
 
Machine Translation (F16)
100% 1952
300.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download