Geekbench ML Score

896
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 02:58 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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 750
80.4 IPS
 
Image Classification (F16)
100% 712
76.3 IPS
 
Image Classification (I8)
81% 471
50.5 IPS
 
Image Segmentation (F32)
100% 1055
6.52 IPS
 
Image Segmentation (F16)
100% 1009
6.23 IPS
 
Image Segmentation (I8)
89% 1456
8.99 IPS
 
Pose Estimation (F32)
100% 391
1.58 IPS
 
Pose Estimation (F16)
100% 384
1.55 IPS
 
Pose Estimation (I8)
80% 479
1.94 IPS
 
Object Detection (F32)
100% 1026
36.0 IPS
 
Object Detection (F16)
100% 1017
35.7 IPS
 
Object Detection (I8)
52% 680
23.9 IPS
 
Face Detection (F32)
100% 1270
14.6 IPS
 
Face Detection (F16)
100% 1211
13.9 IPS
 
Face Detection (I8)
75% 838
9.62 IPS
 
Text Classification (F32)
100% 1033
408.7 IPS
 
Text Classification (F16)
100% 1137
449.8 IPS
 
Machine Translation (F32)
100% 2028
312.6 IPS
 
Machine Translation (F16)
100% 2045
315.1 IPS
 

Compare

Set Baseline