Geekbench ML Score

3160
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 09 2022 04:56 PM
Views 40

System Information

System Information
Operating System iOS 16.0
Model iPhone15,3
Model IDiPhone15,3
Motherboard D74AP
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 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7156
766.8 IPS
 
Image Classification (F16)
100% 7077
758.2 IPS
 
Image Classification (I8)
81% 745
79.8 IPS
 
Image Segmentation (F32)
100% 2336
14.4 IPS
 
Image Segmentation (F16)
100% 2509
15.5 IPS
 
Image Segmentation (I8)
89% 1364
8.42 IPS
 
Pose Estimation (F32)
100% 25598
103.6 IPS
 
Pose Estimation (F16)
100% 25324
102.5 IPS
 
Pose Estimation (I8)
80% 259
1.05 IPS
 
Object Detection (F32)
100% 8460
296.9 IPS
 
Object Detection (F16)
100% 8642
303.3 IPS
 
Object Detection (I8)
52% 1063
37.3 IPS
 
Face Detection (F32)
100% 10315
118.5 IPS
 
Face Detection (F16)
100% 10298
118.3 IPS
 
Face Detection (I8)
75% 1039
11.9 IPS
 
Text Classification (F32)
100% 1203
475.8 IPS
 
Text Classification (F16)
100% 1199
474.0 IPS
 
Machine Translation (F32)
100% 2238
344.9 IPS
 
Machine Translation (F16)
100% 2232
343.9 IPS
 

Compare

Set Baseline