Geekbench ML Score

3198
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

User toygoon
Upload Date December 08 2022 10:29 AM
Views 4

System Information

System Information
Operating System iOS 16.2
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% 7255
777.4 IPS
 
Image Classification (F16)
100% 7296
781.8 IPS
 
Image Classification (I8)
81% 739
79.2 IPS
 
Image Segmentation (F32)
100% 2320
14.3 IPS
 
Image Segmentation (F16)
100% 2309
14.3 IPS
 
Image Segmentation (I8)
89% 1353
8.36 IPS
 
Pose Estimation (F32)
100% 26019
105.3 IPS
 
Pose Estimation (F16)
100% 26410
106.9 IPS
 
Pose Estimation (I8)
80% 256
1.04 IPS
 
Object Detection (F32)
100% 8677
304.5 IPS
 
Object Detection (F16)
100% 8993
315.6 IPS
 
Object Detection (I8)
52% 1056
37.1 IPS
 
Face Detection (F32)
100% 10658
122.5 IPS
 
Face Detection (F16)
100% 10539
121.1 IPS
 
Face Detection (I8)
75% 1037
11.9 IPS
 
Text Classification (F32)
100% 1248
493.7 IPS
 
Text Classification (F16)
100% 1249
494.0 IPS
 
Machine Translation (F32)
100% 2289
352.8 IPS
 
Machine Translation (F16)
100% 2300
354.5 IPS
 

Compare

Set Baseline