Geekbench ML Score

624
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date September 24 2024 11:47 PM
Views 3

System Information

System Information
Operating System iOS 16.7.10
Model iPhone 8
Model IDiPhone10,1
Motherboard D20AP
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 1.93 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 173
32.4 IPS
 
Image Classification (F16)
100% 145
27.1 IPS
 
Image Classification (I8)
99% 142
26.6 IPS
 
Image Segmentation (F32)
100% 186
3.10 IPS
 
Image Segmentation (F16)
100% 199
3.32 IPS
 
Image Segmentation (I8)
100% 199
3.32 IPS
 
Pose Estimation (F32)
100% 2306
2.79 IPS
 
Pose Estimation (F16)
100% 2619
3.17 IPS
 
Pose Estimation (I8)
100% 2782
3.37 IPS
 
Object Detection (F32)
100% 322
24.1 IPS
 
Object Detection (F16)
100% 276
20.6 IPS
 
Object Detection (I8)
97% 282
21.1 IPS
 
Face Detection (F32)
100% 886
10.5 IPS
 
Face Detection (F16)
100% 960
11.4 IPS
 
Face Detection (I8)
99% 990
11.8 IPS
 
Depth Estimation (F32)
100% 2312
17.9 IPS
 
Depth Estimation (F16)
100% 2485
19.3 IPS
 
Depth Estimation (I8)
99% 2319
18.0 IPS
 
Style Transfer (F32)
100% 4660
6.13 IPS
 
Style Transfer (F16)
100% 4945
6.51 IPS
 
Style Transfer (I8)
100% 4842
6.37 IPS
 
Image Super-Resolution (F32)
100% 940
33.6 IPS
 
Image Super-Resolution (F16)
100% 1182
42.2 IPS
 
Image Super-Resolution (I8)
100% 1048
37.4 IPS
 
Text Classification (F32)
100% 49
70.1 IPS
 
Text Classification (F16)
100% 202
290.9 IPS
 
Text Classification (I8)
96% 202
290.9 IPS
 
Machine Translation (F32)
100% 305
5.61 IPS
 
Machine Translation (F16)
100% 240
4.42 IPS
 
Machine Translation (I8)
99% 313
5.75 IPS
 

Compare

Set Baseline Geekbench 6 now available