Geekbench ML Score

2572
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

User davidblue
Upload Date September 30 2022 08:31 PM
Views 11

System Information

System Information
Operating System iOS 16.1
Model iPhone 12 Pro Max
Model IDiPhone13,4
Motherboard D54pAP
CPU Information
Name Apple A14 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.99 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.54 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5923
634.6 IPS
 
Image Classification (F16)
100% 6231
667.6 IPS
 
Image Classification (I8)
81% 641
68.7 IPS
 
Image Segmentation (F32)
100% 1794
11.1 IPS
 
Image Segmentation (F16)
100% 1867
11.5 IPS
 
Image Segmentation (I8)
89% 1123
6.94 IPS
 
Pose Estimation (F32)
100% 18676
75.6 IPS
 
Pose Estimation (F16)
100% 18803
76.1 IPS
 
Pose Estimation (I8)
80% 224
0.91 IPS
 
Object Detection (F32)
100% 7267
255.0 IPS
 
Object Detection (F16)
100% 7479
262.5 IPS
 
Object Detection (I8)
52% 921
32.3 IPS
 
Face Detection (F32)
100% 7599
87.3 IPS
 
Face Detection (F16)
100% 7564
86.9 IPS
 
Face Detection (I8)
75% 897
10.3 IPS
 
Text Classification (F32)
100% 1093
432.4 IPS
 
Text Classification (F16)
100% 1110
439.0 IPS
 
Machine Translation (F32)
100% 1689
260.3 IPS
 
Machine Translation (F16)
100% 1697
261.5 IPS
 

Compare

Set Baseline Geekbench 6 now available