Geekbench ML Score

851
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 06 2022 02:55 AM
Views 1

System Information

System Information
Operating System iOS 15.6
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 5.52 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 796
85.3 IPS
 
Image Classification (F16)
100% 768
82.3 IPS
 
Image Classification (I8)
81% 323
34.6 IPS
 
Image Segmentation (F32)
100% 1143
7.06 IPS
 
Image Segmentation (F16)
100% 1133
7.00 IPS
 
Image Segmentation (I8)
89% 1366
8.44 IPS
 
Pose Estimation (F32)
100% 392
1.58 IPS
 
Pose Estimation (F16)
100% 386
1.56 IPS
 
Pose Estimation (I8)
80% 481
1.95 IPS
 
Object Detection (F32)
100% 1148
40.3 IPS
 
Object Detection (F16)
100% 1154
40.5 IPS
 
Object Detection (I8)
52% 458
16.1 IPS
 
Face Detection (F32)
100% 1361
15.6 IPS
 
Face Detection (F16)
100% 1332
15.3 IPS
 
Face Detection (I8)
75% 778
8.94 IPS
 
Text Classification (F32)
100% 744
294.3 IPS
 
Text Classification (F16)
100% 734
290.5 IPS
 
Machine Translation (F32)
100% 1987
306.2 IPS
 
Machine Translation (F16)
100% 1976
304.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download