Geekbench ML Score

2705
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date March 10 2022 07:16 PM
Views 6

System Information

System Information
Operating System iOS 15.3.1
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% 5096
546.0 IPS
 
Image Classification (F16)
100% 5198
557.0 IPS
 
Image Classification (I8)
81% 697
74.6 IPS
 
Image Segmentation (F32)
100% 2184
13.5 IPS
 
Image Segmentation (F16)
100% 2178
13.5 IPS
 
Image Segmentation (I8)
89% 1221
7.54 IPS
 
Pose Estimation (F32)
100% 22473
90.9 IPS
 
Pose Estimation (F16)
100% 21779
88.1 IPS
 
Pose Estimation (I8)
80% 234
0.95 IPS
 
Object Detection (F32)
100% 7016
246.2 IPS
 
Object Detection (F16)
100% 6827
239.6 IPS
 
Object Detection (I8)
52% 981
34.4 IPS
 
Face Detection (F32)
100% 7982
91.7 IPS
 
Face Detection (F16)
100% 8061
92.6 IPS
 
Face Detection (I8)
75% 938
10.8 IPS
 
Text Classification (F32)
100% 1104
436.7 IPS
 
Text Classification (F16)
100% 1107
437.8 IPS
 
Machine Translation (F32)
100% 1961
302.3 IPS
 
Machine Translation (F16)
100% 1962
302.4 IPS
 

Compare

Set Baseline Geekbench 6 now available