Geekbench ML Score

3195
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 19 2022 04:20 AM
Views 5

System Information

System Information
Operating System iOS 16.0.1
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% 7214
773.0 IPS
 
Image Classification (F16)
100% 7241
775.9 IPS
 
Image Classification (I8)
81% 746
79.9 IPS
 
Image Segmentation (F32)
100% 2551
15.8 IPS
 
Image Segmentation (F16)
100% 2539
15.7 IPS
 
Image Segmentation (I8)
89% 1360
8.40 IPS
 
Pose Estimation (F32)
100% 24899
100.8 IPS
 
Pose Estimation (F16)
100% 25091
101.5 IPS
 
Pose Estimation (I8)
80% 259
1.05 IPS
 
Object Detection (F32)
100% 8741
306.8 IPS
 
Object Detection (F16)
100% 8769
307.7 IPS
 
Object Detection (I8)
52% 1064
37.4 IPS
 
Face Detection (F32)
100% 10417
119.7 IPS
 
Face Detection (F16)
100% 10416
119.7 IPS
 
Face Detection (I8)
75% 1037
11.9 IPS
 
Text Classification (F32)
100% 1208
477.9 IPS
 
Text Classification (F16)
100% 1238
489.5 IPS
 
Machine Translation (F32)
100% 2242
345.6 IPS
 
Machine Translation (F16)
100% 2257
347.8 IPS
 

Compare

Set Baseline