Geekbench ML Score

2839
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 24 2022 06:29 PM
Views 1

System Information

System Information
Operating System iOS 16.1.1
Model iPhone 13
Model IDiPhone14,5
Motherboard D17AP
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 3.56 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6260
670.7 IPS
 
Image Classification (F16)
100% 6280
672.9 IPS
 
Image Classification (I8)
81% 698
74.8 IPS
 
Image Segmentation (F32)
100% 2153
13.3 IPS
 
Image Segmentation (F16)
100% 2104
13.0 IPS
 
Image Segmentation (I8)
89% 1202
7.42 IPS
 
Pose Estimation (F32)
100% 22839
92.4 IPS
 
Pose Estimation (F16)
100% 23892
96.7 IPS
 
Pose Estimation (I8)
80% 233
0.94 IPS
 
Object Detection (F32)
100% 7557
265.2 IPS
 
Object Detection (F16)
100% 7568
265.6 IPS
 
Object Detection (I8)
52% 959
33.6 IPS
 
Face Detection (F32)
100% 8698
99.9 IPS
 
Face Detection (F16)
100% 8745
100.5 IPS
 
Face Detection (I8)
75% 878
10.1 IPS
 
Text Classification (F32)
100% 1181
467.1 IPS
 
Text Classification (F16)
100% 1187
469.3 IPS
 
Machine Translation (F32)
100% 2053
316.4 IPS
 
Machine Translation (F16)
100% 2046
315.3 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download