Geekbench ML Score

3182
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 06:05 PM
Views 1

System Information

System Information
Operating System iOS 16.1.2
Model iPhone15,2
Model IDiPhone15,2
Motherboard D73AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.44 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

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7206
772.0 IPS
 
Image Classification (F16)
100% 7193
770.7 IPS
 
Image Classification (I8)
81% 745
79.8 IPS
 
Image Segmentation (F32)
100% 2338
14.4 IPS
 
Image Segmentation (F16)
100% 2340
14.5 IPS
 
Image Segmentation (I8)
89% 1365
8.43 IPS
 
Pose Estimation (F32)
100% 25554
103.4 IPS
 
Pose Estimation (F16)
100% 26081
105.5 IPS
 
Pose Estimation (I8)
80% 258
1.04 IPS
 
Object Detection (F32)
100% 8916
312.9 IPS
 
Object Detection (F16)
100% 8969
314.7 IPS
 
Object Detection (I8)
52% 1063
37.3 IPS
 
Face Detection (F32)
100% 10327
118.6 IPS
 
Face Detection (F16)
100% 10359
119.0 IPS
 
Face Detection (I8)
75% 1047
12.0 IPS
 
Text Classification (F32)
100% 1211
479.0 IPS
 
Text Classification (F16)
100% 1230
486.3 IPS
 
Machine Translation (F32)
100% 2244
345.9 IPS
 
Machine Translation (F16)
100% 2260
348.3 IPS
 

Compare

Set Baseline