Geekbench ML Score

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

Result Information

Upload Date October 07 2022 01:30 AM
Views 3

System Information

System Information
Operating System iOS 16.0.2
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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7372
789.9 IPS
 
Image Classification (F16)
100% 7152
766.3 IPS
 
Image Classification (I8)
81% 746
79.9 IPS
 
Image Segmentation (F32)
100% 2377
14.7 IPS
 
Image Segmentation (F16)
100% 2498
15.4 IPS
 
Image Segmentation (I8)
89% 1326
8.19 IPS
 
Pose Estimation (F32)
100% 26703
108.1 IPS
 
Pose Estimation (F16)
100% 26157
105.8 IPS
 
Pose Estimation (I8)
80% 256
1.04 IPS
 
Object Detection (F32)
100% 8565
300.6 IPS
 
Object Detection (F16)
100% 8975
315.0 IPS
 
Object Detection (I8)
52% 1055
37.0 IPS
 
Face Detection (F32)
100% 10591
121.7 IPS
 
Face Detection (F16)
100% 10336
118.8 IPS
 
Face Detection (I8)
75% 1023
11.7 IPS
 
Text Classification (F32)
100% 1295
512.0 IPS
 
Text Classification (F16)
100% 1342
530.9 IPS
 
Machine Translation (F32)
100% 2251
346.9 IPS
 
Machine Translation (F16)
100% 2276
350.8 IPS
 

Compare

Set Baseline Geekbench 6 now available