Geekbench ML Score

959
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 06 2021 05:28 AM
Views 1

System Information

System Information
Operating System iOS 15.0.2
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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 790
84.7 IPS
 
Image Classification (F16)
100% 773
82.8 IPS
 
Image Classification (I8)
81% 468
50.2 IPS
 
Image Segmentation (F32)
100% 1131
6.99 IPS
 
Image Segmentation (F16)
100% 1111
6.86 IPS
 
Image Segmentation (I8)
89% 1460
9.02 IPS
 
Pose Estimation (F32)
100% 442
1.79 IPS
 
Pose Estimation (F16)
100% 434
1.76 IPS
 
Pose Estimation (I8)
80% 496
2.01 IPS
 
Object Detection (F32)
100% 1136
39.9 IPS
 
Object Detection (F16)
100% 1131
39.7 IPS
 
Object Detection (I8)
52% 783
27.5 IPS
 
Face Detection (F32)
100% 1356
15.6 IPS
 
Face Detection (F16)
100% 1326
15.2 IPS
 
Face Detection (I8)
75% 855
9.82 IPS
 
Text Classification (F32)
100% 1233
487.8 IPS
 
Text Classification (F16)
100% 1250
494.6 IPS
 
Machine Translation (F32)
100% 1974
304.2 IPS
 
Machine Translation (F16)
100% 1961
302.3 IPS
 

Compare

Set Baseline Geekbench 6 now available