Geekbench ML Score

618
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date October 12 2024 10:06 AM
Views 1

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% 177
33.1 IPS
 
Image Classification (F16)
100% 143
26.7 IPS
 
Image Classification (I8)
99% 143
26.7 IPS
 
Image Segmentation (F32)
100% 187
3.13 IPS
 
Image Segmentation (F16)
100% 198
3.31 IPS
 
Image Segmentation (I8)
100% 199
3.32 IPS
 
Pose Estimation (F32)
100% 2265
2.74 IPS
 
Pose Estimation (F16)
100% 2609
3.16 IPS
 
Pose Estimation (I8)
100% 2788
3.38 IPS
 
Object Detection (F32)
100% 292
21.8 IPS
 
Object Detection (F16)
100% 316
23.6 IPS
 
Object Detection (I8)
97% 279
20.8 IPS
 
Face Detection (F32)
100% 945
11.2 IPS
 
Face Detection (F16)
100% 984
11.7 IPS
 
Face Detection (I8)
99% 968
11.5 IPS
 
Depth Estimation (F32)
100% 2124
16.5 IPS
 
Depth Estimation (F16)
100% 2334
18.1 IPS
 
Depth Estimation (I8)
99% 2484
19.3 IPS
 
Style Transfer (F32)
100% 4139
5.44 IPS
 
Style Transfer (F16)
100% 4436
5.83 IPS
 
Style Transfer (I8)
100% 4561
6.00 IPS
 
Image Super-Resolution (F32)
100% 992
35.4 IPS
 
Image Super-Resolution (F16)
100% 1061
37.9 IPS
 
Image Super-Resolution (I8)
100% 1063
38.0 IPS
 
Text Classification (F32)
100% 50
71.4 IPS
 
Text Classification (F16)
100% 200
287.9 IPS
 
Text Classification (I8)
96% 202
289.8 IPS
 
Machine Translation (F32)
100% 315
5.80 IPS
 
Machine Translation (F16)
100% 241
4.43 IPS
 
Machine Translation (I8)
99% 299
5.51 IPS
 

Compare

Set Baseline Geekbench 6 now available