Geekbench ML Score

3586
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 13 2023 06:23 PM
Views 40

System Information

System Information
Operating System iOS 17.0
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% 7911
847.7 IPS
 
Image Classification (F16)
100% 7936
850.3 IPS
 
Image Classification (I8)
81% 821
88.0 IPS
 
Image Segmentation (F32)
100% 2592
16.0 IPS
 
Image Segmentation (F16)
100% 2583
16.0 IPS
 
Image Segmentation (I8)
89% 1430
8.83 IPS
 
Pose Estimation (F32)
100% 27914
113.0 IPS
 
Pose Estimation (F16)
100% 28326
114.6 IPS
 
Pose Estimation (I8)
80% 271
1.10 IPS
 
Object Detection (F32)
100% 8655
303.8 IPS
 
Object Detection (F16)
100% 8643
303.3 IPS
 
Object Detection (I8)
52% 1123
39.4 IPS
 
Face Detection (F32)
100% 11862
136.3 IPS
 
Face Detection (F16)
100% 11746
134.9 IPS
 
Face Detection (I8)
75% 1112
12.8 IPS
 
Text Classification (F32)
100% 1728
683.3 IPS
 
Text Classification (F16)
100% 1786
706.4 IPS
 
Machine Translation (F32)
100% 2845
438.4 IPS
 
Machine Translation (F16)
100% 2862
441.0 IPS
 

Compare

Set Baseline Geekbench 6 now available