Geekbench ML Score

926
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 30 2022 03:32 AM
Views 2

System Information

System Information
Operating System iOS 16.0
Model iPhone 13 Pro Max
Model IDiPhone14,3
Motherboard D64AP
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 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 760
81.5 IPS
 
Image Classification (F16)
100% 739
79.2 IPS
 
Image Classification (I8)
81% 458
49.1 IPS
 
Image Segmentation (F32)
100% 1111
6.86 IPS
 
Image Segmentation (F16)
100% 1081
6.68 IPS
 
Image Segmentation (I8)
89% 1459
9.01 IPS
 
Pose Estimation (F32)
100% 416
1.68 IPS
 
Pose Estimation (F16)
100% 410
1.66 IPS
 
Pose Estimation (I8)
80% 480
1.94 IPS
 
Object Detection (F32)
100% 1081
37.9 IPS
 
Object Detection (F16)
100% 1079
37.8 IPS
 
Object Detection (I8)
52% 781
27.4 IPS
 
Face Detection (F32)
100% 1303
15.0 IPS
 
Face Detection (F16)
100% 1278
14.7 IPS
 
Face Detection (I8)
75% 855
9.82 IPS
 
Text Classification (F32)
100% 1109
438.8 IPS
 
Text Classification (F16)
100% 1095
433.2 IPS
 
Machine Translation (F32)
100% 2016
310.7 IPS
 
Machine Translation (F16)
100% 2012
310.0 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download