Geekbench ML Score

1484
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 02 2023 12:54 AM
Views 1

System Information

System Information
Operating System iOS 17.1.2
Model iPhone15,3
Model IDiPhone15,3
Motherboard D74AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.01 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% 3063
328.2 IPS
 
Image Classification (F16)
100% 3503
375.3 IPS
 
Image Classification (I8)
81% 307
32.9 IPS
 
Image Segmentation (F32)
100% 1020
6.30 IPS
 
Image Segmentation (F16)
100% 1039
6.42 IPS
 
Image Segmentation (I8)
89% 562
3.47 IPS
 
Pose Estimation (F32)
100% 12723
51.5 IPS
 
Pose Estimation (F16)
100% 13094
53.0 IPS
 
Pose Estimation (I8)
80% 106
0.43 IPS
 
Object Detection (F32)
100% 5526
193.9 IPS
 
Object Detection (F16)
100% 3611
126.7 IPS
 
Object Detection (I8)
52% 436
15.3 IPS
 
Face Detection (F32)
100% 5955
68.4 IPS
 
Face Detection (F16)
100% 6107
70.2 IPS
 
Face Detection (I8)
75% 431
4.95 IPS
 
Text Classification (F32)
100% 666
263.4 IPS
 
Text Classification (F16)
100% 626
247.8 IPS
 
Machine Translation (F32)
100% 888
136.8 IPS
 
Machine Translation (F16)
100% 1036
159.6 IPS
 

Compare

Set Baseline Geekbench 6 now available