Geekbench ML Score

3198
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 27 2022 12:47 AM
Views 2

System Information

System Information
Operating System iOS 16.0.1
Model iPhone15,2
Model IDiPhone15,2
Motherboard D73AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.45 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.51 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7204
771.9 IPS
 
Image Classification (F16)
100% 7273
779.3 IPS
 
Image Classification (I8)
81% 745
79.9 IPS
 
Image Segmentation (F32)
100% 2471
15.3 IPS
 
Image Segmentation (F16)
100% 2455
15.2 IPS
 
Image Segmentation (I8)
89% 1364
8.42 IPS
 
Pose Estimation (F32)
100% 25840
104.6 IPS
 
Pose Estimation (F16)
100% 26317
106.5 IPS
 
Pose Estimation (I8)
80% 258
1.05 IPS
 
Object Detection (F32)
100% 8779
308.1 IPS
 
Object Detection (F16)
100% 8655
303.7 IPS
 
Object Detection (I8)
52% 1065
37.4 IPS
 
Face Detection (F32)
100% 10495
120.6 IPS
 
Face Detection (F16)
100% 10458
120.1 IPS
 
Face Detection (I8)
75% 1043
12.0 IPS
 
Text Classification (F32)
100% 1227
485.4 IPS
 
Text Classification (F16)
100% 1219
482.3 IPS
 
Machine Translation (F32)
100% 2230
343.7 IPS
 
Machine Translation (F16)
100% 2246
346.2 IPS
 

Compare

Set Baseline Geekbench 6 now available