Geekbench ML Score

2770
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 15 2024 07:32 PM
Views 1

System Information

System Information
Operating System iOS 15.1.1
Model iPhone 13 mini
Model IDiPhone14,4
Motherboard D16AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.61 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5594
599.4 IPS
 
Image Classification (F16)
100% 5587
598.6 IPS
 
Image Classification (I8)
81% 696
74.5 IPS
 
Image Segmentation (F32)
100% 2220
13.7 IPS
 
Image Segmentation (F16)
100% 2176
13.4 IPS
 
Image Segmentation (I8)
89% 1274
7.87 IPS
 
Pose Estimation (F32)
100% 23003
93.1 IPS
 
Pose Estimation (F16)
100% 23301
94.3 IPS
 
Pose Estimation (I8)
80% 241
0.97 IPS
 
Object Detection (F32)
100% 7036
246.9 IPS
 
Object Detection (F16)
100% 7025
246.5 IPS
 
Object Detection (I8)
52% 997
35.0 IPS
 
Face Detection (F32)
100% 8152
93.7 IPS
 
Face Detection (F16)
100% 8064
92.6 IPS
 
Face Detection (I8)
75% 948
10.9 IPS
 
Text Classification (F32)
100% 1105
437.0 IPS
 
Text Classification (F16)
100% 1112
439.7 IPS
 
Machine Translation (F32)
100% 1984
305.8 IPS
 
Machine Translation (F16)
100% 1981
305.3 IPS
 

Compare

Set Baseline Geekbench 6 now available