Geekbench ML Score

2737
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date March 10 2022 03:22 PM
Views 3

System Information

System Information
Operating System iOS 15.3.1
Model iPhone 13 Pro Max
Model IDiPhone14,3
Motherboard D64AP
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 5.53 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5497
589.0 IPS
 
Image Classification (F16)
100% 5470
586.1 IPS
 
Image Classification (I8)
81% 690
74.0 IPS
 
Image Segmentation (F32)
100% 2095
12.9 IPS
 
Image Segmentation (F16)
100% 2133
13.2 IPS
 
Image Segmentation (I8)
89% 1216
7.51 IPS
 
Pose Estimation (F32)
100% 23518
95.2 IPS
 
Pose Estimation (F16)
100% 24110
97.6 IPS
 
Pose Estimation (I8)
80% 233
0.94 IPS
 
Object Detection (F32)
100% 7033
246.8 IPS
 
Object Detection (F16)
100% 7035
246.9 IPS
 
Object Detection (I8)
52% 960
33.7 IPS
 
Face Detection (F32)
100% 7983
91.7 IPS
 
Face Detection (F16)
100% 8040
92.4 IPS
 
Face Detection (I8)
75% 927
10.6 IPS
 
Text Classification (F32)
100% 1117
442.0 IPS
 
Text Classification (F16)
100% 1113
440.2 IPS
 
Machine Translation (F32)
100% 1976
304.5 IPS
 
Machine Translation (F16)
100% 1971
303.8 IPS
 

Compare

Set Baseline Geekbench 6 now available