Geekbench ML Score

3606
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 02 2023 10:14 PM
Views 1

System Information

System Information
Operating System iOS 17.0.2
Model iPhone16,2
Model IDiPhone16,2
Motherboard D84AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.78 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.47 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7935
850.2 IPS
 
Image Classification (F16)
100% 7952
852.0 IPS
 
Image Classification (I8)
81% 821
87.9 IPS
 
Image Segmentation (F32)
100% 2580
15.9 IPS
 
Image Segmentation (F16)
100% 2608
16.1 IPS
 
Image Segmentation (I8)
89% 1456
8.99 IPS
 
Pose Estimation (F32)
100% 27511
111.3 IPS
 
Pose Estimation (F16)
100% 28059
113.5 IPS
 
Pose Estimation (I8)
80% 272
1.10 IPS
 
Object Detection (F32)
100% 8758
307.4 IPS
 
Object Detection (F16)
100% 8532
299.4 IPS
 
Object Detection (I8)
52% 1157
40.6 IPS
 
Face Detection (F32)
100% 11629
133.6 IPS
 
Face Detection (F16)
100% 11888
136.6 IPS
 
Face Detection (I8)
75% 1135
13.0 IPS
 
Text Classification (F32)
100% 1780
704.0 IPS
 
Text Classification (F16)
100% 1823
721.2 IPS
 
Machine Translation (F32)
100% 2863
441.2 IPS
 
Machine Translation (F16)
100% 2862
441.1 IPS
 

Compare

Set Baseline Geekbench 6 now available