Geekbench ML Score

3667
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 29 2023 05:20 PM
Views 2

System Information

System Information
Operating System iOS 17.1
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% 7965
853.4 IPS
 
Image Classification (F16)
100% 7926
849.2 IPS
 
Image Classification (I8)
81% 835
89.4 IPS
 
Image Segmentation (F32)
100% 2647
16.4 IPS
 
Image Segmentation (F16)
100% 2644
16.3 IPS
 
Image Segmentation (I8)
89% 1539
9.51 IPS
 
Pose Estimation (F32)
100% 28201
114.1 IPS
 
Pose Estimation (F16)
100% 28696
116.1 IPS
 
Pose Estimation (I8)
80% 287
1.16 IPS
 
Object Detection (F32)
100% 8675
304.4 IPS
 
Object Detection (F16)
100% 9138
320.7 IPS
 
Object Detection (I8)
52% 1199
42.1 IPS
 
Face Detection (F32)
100% 11793
135.5 IPS
 
Face Detection (F16)
100% 11897
136.7 IPS
 
Face Detection (I8)
75% 1178
13.5 IPS
 
Text Classification (F32)
100% 1769
699.5 IPS
 
Text Classification (F16)
100% 1766
698.4 IPS
 
Machine Translation (F32)
100% 2858
440.5 IPS
 
Machine Translation (F16)
100% 2855
440.0 IPS
 

Compare

Set Baseline Geekbench 6 now available