Geekbench ML Score

3197
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 04:13 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% 7235
775.3 IPS
 
Image Classification (F16)
100% 7242
776.0 IPS
 
Image Classification (I8)
81% 745
79.8 IPS
 
Image Segmentation (F32)
100% 2360
14.6 IPS
 
Image Segmentation (F16)
100% 2338
14.4 IPS
 
Image Segmentation (I8)
89% 1365
8.43 IPS
 
Pose Estimation (F32)
100% 25412
102.8 IPS
 
Pose Estimation (F16)
100% 25455
103.0 IPS
 
Pose Estimation (I8)
80% 258
1.04 IPS
 
Object Detection (F32)
100% 9254
324.8 IPS
 
Object Detection (F16)
100% 9024
316.7 IPS
 
Object Detection (I8)
52% 1064
37.3 IPS
 
Face Detection (F32)
100% 10427
119.8 IPS
 
Face Detection (F16)
100% 10437
119.9 IPS
 
Face Detection (I8)
75% 1046
12.0 IPS
 
Text Classification (F32)
100% 1244
491.9 IPS
 
Text Classification (F16)
100% 1244
492.0 IPS
 
Machine Translation (F32)
100% 2246
346.2 IPS
 
Machine Translation (F16)
100% 2268
349.5 IPS
 

Compare

Set Baseline