Geekbench ML Score

3204
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 05:14 PM
Views 1

System Information

System Information
Operating System iOS 16.1.2
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% 7199
771.3 IPS
 
Image Classification (F16)
100% 7212
772.8 IPS
 
Image Classification (I8)
81% 744
79.7 IPS
 
Image Segmentation (F32)
100% 2384
14.7 IPS
 
Image Segmentation (F16)
100% 2357
14.6 IPS
 
Image Segmentation (I8)
89% 1364
8.43 IPS
 
Pose Estimation (F32)
100% 25582
103.5 IPS
 
Pose Estimation (F16)
100% 26310
106.5 IPS
 
Pose Estimation (I8)
80% 258
1.04 IPS
 
Object Detection (F32)
100% 9247
324.5 IPS
 
Object Detection (F16)
100% 9118
320.0 IPS
 
Object Detection (I8)
52% 1065
37.4 IPS
 
Face Detection (F32)
100% 10400
119.5 IPS
 
Face Detection (F16)
100% 10386
119.3 IPS
 
Face Detection (I8)
75% 1047
12.0 IPS
 
Text Classification (F32)
100% 1228
485.9 IPS
 
Text Classification (F16)
100% 1256
496.8 IPS
 
Machine Translation (F32)
100% 2252
347.1 IPS
 
Machine Translation (F16)
100% 2238
344.9 IPS
 

Compare

Set Baseline