Geekbench ML Score

1375
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 16 2022 06:35 AM
Views 1

System Information

System Information
Operating System iOS 15.4.1
Model iPhone XS
Model IDiPhone11,2
Motherboard D321AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 3.69 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3753
402.1 IPS
 
Image Classification (F16)
100% 3793
406.4 IPS
 
Image Classification (I8)
81% 401
43.0 IPS
 
Image Segmentation (F32)
100% 1379
8.52 IPS
 
Image Segmentation (F16)
100% 1391
8.59 IPS
 
Image Segmentation (I8)
89% 749
4.63 IPS
 
Pose Estimation (F32)
100% 7336
29.7 IPS
 
Pose Estimation (F16)
100% 7219
29.2 IPS
 
Pose Estimation (I8)
80% 141
0.57 IPS
 
Object Detection (F32)
94% 3997
140.3 IPS
 
Object Detection (F16)
94% 3960
139.0 IPS
 
Object Detection (I8)
52% 567
19.9 IPS
 
Face Detection (F32)
67% 3724
42.8 IPS
 
Face Detection (F16)
67% 3735
42.9 IPS
 
Face Detection (I8)
75% 550
6.32 IPS
 
Text Classification (F32)
100% 324
128.2 IPS
 
Text Classification (F16)
100% 324
128.2 IPS
 
Machine Translation (F32)
100% 988
152.3 IPS
 
Machine Translation (F16)
100% 982
151.3 IPS
 

Compare

Set Baseline Geekbench 6 now available