Geekbench ML Score

1734
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 14 2022 09:54 AM
Views 2

System Information

System Information
Operating System iOS 15.5
Model iPhone 11 Pro Max
Model IDiPhone12,5
Motherboard D431AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.66 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4106
440.0 IPS
 
Image Classification (F16)
100% 4074
436.6 IPS
 
Image Classification (I8)
81% 448
48.0 IPS
 
Image Segmentation (F32)
100% 1583
9.78 IPS
 
Image Segmentation (F16)
100% 1585
9.79 IPS
 
Image Segmentation (I8)
89% 825
5.10 IPS
 
Pose Estimation (F32)
100% 8644
35.0 IPS
 
Pose Estimation (F16)
100% 8707
35.2 IPS
 
Pose Estimation (I8)
80% 145
0.59 IPS
 
Object Detection (F32)
94% 4999
175.4 IPS
 
Object Detection (F16)
94% 5015
176.0 IPS
 
Object Detection (I8)
52% 624
21.9 IPS
 
Face Detection (F32)
67% 5318
61.1 IPS
 
Face Detection (F16)
67% 5356
61.5 IPS
 
Face Detection (I8)
75% 605
6.95 IPS
 
Text Classification (F32)
100% 722
285.7 IPS
 
Text Classification (F16)
100% 745
294.5 IPS
 
Machine Translation (F32)
100% 1188
183.0 IPS
 
Machine Translation (F16)
100% 1196
184.3 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download