Geekbench ML Score

1734
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 03:00 PM
Views 1

System Information

System Information
Operating System iOS 16.2
Model iPhone 13
Model IDiPhone14,5
Motherboard D17AP
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 3.56 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1377
147.6 IPS
 
Image Classification (F16)
100% 1443
154.6 IPS
 
Image Classification (I8)
81% 646
69.2 IPS
 
Image Segmentation (F32)
100% 5277
32.6 IPS
 
Image Segmentation (F16)
100% 7338
45.3 IPS
 
Image Segmentation (I8)
89% 1142
7.05 IPS
 
Pose Estimation (F32)
100% 1769
7.16 IPS
 
Pose Estimation (F16)
100% 4195
17.0 IPS
 
Pose Estimation (I8)
80% 215
0.87 IPS
 
Object Detection (F32)
100% 1776
62.3 IPS
 
Object Detection (F16)
100% 3126
109.7 IPS
 
Object Detection (I8)
52% 911
32.0 IPS
 
Face Detection (F32)
100% 4833
55.5 IPS
 
Face Detection (F16)
97% 5841
67.1 IPS
 
Face Detection (I8)
75% 859
9.87 IPS
 
Text Classification (F32)
100% 986
390.1 IPS
 
Text Classification (F16)
100% 1109
438.8 IPS
 
Machine Translation (F32)
100% 1672
257.6 IPS
 
Machine Translation (F16)
100% 1732
266.9 IPS
 

Compare

Set Baseline