Geekbench ML Score

638
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 18 2024 10:07 AM
Views 1

System Information

System Information
Operating System iOS 16.7.10
Model iPhone X
Model IDiPhone10,3
Motherboard D22AP
CPU Information
Name Apple A11 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.39 GHz
Cluster 12 Cores
Cluster 24 Cores
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 2.76 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 200
37.4 IPS
 
Image Classification (F16)
100% 147
27.5 IPS
 
Image Classification (I8)
99% 147
27.4 IPS
 
Image Segmentation (F32)
100% 188
3.14 IPS
 
Image Segmentation (F16)
100% 201
3.36 IPS
 
Image Segmentation (I8)
100% 200
3.34 IPS
 
Pose Estimation (F32)
100% 2320
2.81 IPS
 
Pose Estimation (F16)
100% 2746
3.33 IPS
 
Pose Estimation (I8)
100% 2671
3.23 IPS
 
Object Detection (F32)
100% 325
24.3 IPS
 
Object Detection (F16)
100% 306
22.9 IPS
 
Object Detection (I8)
97% 286
21.4 IPS
 
Face Detection (F32)
100% 983
11.7 IPS
 
Face Detection (F16)
100% 906
10.8 IPS
 
Face Detection (I8)
99% 962
11.4 IPS
 
Depth Estimation (F32)
100% 2464
19.1 IPS
 
Depth Estimation (F16)
100% 2457
19.1 IPS
 
Depth Estimation (I8)
99% 2506
19.4 IPS
 
Style Transfer (F32)
100% 4796
6.31 IPS
 
Style Transfer (F16)
100% 4700
6.18 IPS
 
Style Transfer (I8)
100% 5004
6.58 IPS
 
Image Super-Resolution (F32)
100% 1115
39.8 IPS
 
Image Super-Resolution (F16)
100% 1095
39.1 IPS
 
Image Super-Resolution (I8)
100% 1076
38.4 IPS
 
Text Classification (F32)
100% 53
75.6 IPS
 
Text Classification (F16)
100% 199
285.3 IPS
 
Text Classification (I8)
96% 200
287.2 IPS
 
Machine Translation (F32)
100% 312
5.75 IPS
 
Machine Translation (F16)
100% 240
4.41 IPS
 
Machine Translation (I8)
99% 292
5.37 IPS
 

Compare

Set Baseline Geekbench 6 now available