Geekbench ML Score

1719
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date January 08 2024 01:11 PM
Views 1

System Information

System Information
Operating System iOS 17.2.1
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
Cluster 12 Cores
Cluster 24 Cores
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 Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 926
173.3 IPS
 
Image Classification (F16)
100% 883
165.3 IPS
 
Image Classification (I8)
99% 887
165.9 IPS
 
Image Segmentation (F32)
100% 382
6.38 IPS
 
Image Segmentation (F16)
100% 364
6.07 IPS
 
Image Segmentation (I8)
100% 363
6.06 IPS
 
Pose Estimation (F32)
100% 4897
5.93 IPS
 
Pose Estimation (F16)
100% 9692
11.7 IPS
 
Pose Estimation (I8)
100% 9546
11.6 IPS
 
Object Detection (F32)
100% 968
72.3 IPS
 
Object Detection (F16)
100% 975
72.8 IPS
 
Object Detection (I8)
97% 969
72.4 IPS
 
Face Detection (F32)
100% 1706
20.3 IPS
 
Face Detection (F16)
100% 1561
18.6 IPS
 
Face Detection (I8)
99% 1559
18.5 IPS
 
Depth Estimation (F32)
100% 3333
25.8 IPS
 
Depth Estimation (F16)
99% 3636
28.2 IPS
 
Depth Estimation (I8)
99% 3647
28.3 IPS
 
Style Transfer (F32)
100% 9415
12.4 IPS
 
Style Transfer (F16)
100% 11357
14.9 IPS
 
Style Transfer (I8)
100% 11406
15.0 IPS
 
Image Super-Resolution (F32)
100% 2555
91.2 IPS
 
Image Super-Resolution (F16)
100% 2477
88.5 IPS
 
Image Super-Resolution (I8)
100% 2481
88.6 IPS
 
Text Classification (F32)
100% 1053
1.51 KIPS
 
Text Classification (F16)
100% 694
997.9 IPS
 
Text Classification (I8)
96% 695
998.5 IPS
 
Machine Translation (F32)
100% 708
13.0 IPS
 
Machine Translation (F16)
99% 854
15.7 IPS
 
Machine Translation (I8)
99% 707
13.0 IPS
 

Compare

Set Baseline Geekbench 6 now available