Geekbench ML Score

3220
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 30 2022 02:53 AM
Views 1

System Information

System Information
Operating System iOS 16.1
Model iPhone15,3
Model IDiPhone15,3
Motherboard D74AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.45 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% 7347
787.2 IPS
 
Image Classification (F16)
100% 7209
772.4 IPS
 
Image Classification (I8)
81% 745
79.8 IPS
 
Image Segmentation (F32)
100% 2509
15.5 IPS
 
Image Segmentation (F16)
100% 2571
15.9 IPS
 
Image Segmentation (I8)
89% 1367
8.44 IPS
 
Pose Estimation (F32)
100% 25435
102.9 IPS
 
Pose Estimation (F16)
100% 25785
104.3 IPS
 
Pose Estimation (I8)
80% 258
1.05 IPS
 
Object Detection (F32)
100% 9182
322.2 IPS
 
Object Detection (F16)
100% 9002
315.9 IPS
 
Object Detection (I8)
52% 1065
37.4 IPS
 
Face Detection (F32)
100% 10393
119.4 IPS
 
Face Detection (F16)
100% 10429
119.8 IPS
 
Face Detection (I8)
75% 1048
12.0 IPS
 
Text Classification (F32)
100% 1217
481.5 IPS
 
Text Classification (F16)
100% 1220
482.5 IPS
 
Machine Translation (F32)
100% 2262
348.6 IPS
 
Machine Translation (F16)
100% 2265
349.0 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download