Geekbench ML Score

3211
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 08:46 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 3.45 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

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7264
778.3 IPS
 
Image Classification (F16)
100% 7215
773.1 IPS
 
Image Classification (I8)
81% 745
79.8 IPS
 
Image Segmentation (F32)
100% 2468
15.2 IPS
 
Image Segmentation (F16)
100% 2500
15.4 IPS
 
Image Segmentation (I8)
89% 1366
8.43 IPS
 
Pose Estimation (F32)
100% 25678
103.9 IPS
 
Pose Estimation (F16)
100% 26130
105.7 IPS
 
Pose Estimation (I8)
80% 259
1.05 IPS
 
Object Detection (F32)
100% 8921
313.1 IPS
 
Object Detection (F16)
100% 9066
318.2 IPS
 
Object Detection (I8)
52% 1070
37.5 IPS
 
Face Detection (F32)
100% 10390
119.4 IPS
 
Face Detection (F16)
100% 10361
119.0 IPS
 
Face Detection (I8)
75% 1048
12.0 IPS
 
Text Classification (F32)
100% 1221
482.9 IPS
 
Text Classification (F16)
100% 1220
482.4 IPS
 
Machine Translation (F32)
100% 2267
349.4 IPS
 
Machine Translation (F16)
100% 2244
345.8 IPS
 

Compare

Set Baseline