Geekbench ML Score

594
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 28 2024 08:03 AM
Views 1

System Information

System Information
Operating System iOS 16.7.7
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% 176
33.0 IPS
 
Image Classification (F16)
100% 146
27.3 IPS
 
Image Classification (I8)
99% 146
27.4 IPS
 
Image Segmentation (F32)
100% 187
3.12 IPS
 
Image Segmentation (F16)
100% 199
3.32 IPS
 
Image Segmentation (I8)
100% 200
3.33 IPS
 
Pose Estimation (F32)
100% 2120
2.57 IPS
 
Pose Estimation (F16)
100% 2418
2.93 IPS
 
Pose Estimation (I8)
100% 2342
2.84 IPS
 
Object Detection (F32)
100% 297
22.2 IPS
 
Object Detection (F16)
100% 271
20.2 IPS
 
Object Detection (I8)
97% 302
22.5 IPS
 
Face Detection (F32)
100% 1016
12.1 IPS
 
Face Detection (F16)
100% 1019
12.1 IPS
 
Face Detection (I8)
99% 938
11.2 IPS
 
Depth Estimation (F32)
100% 2162
16.8 IPS
 
Depth Estimation (F16)
100% 2732
21.2 IPS
 
Depth Estimation (I8)
99% 2362
18.3 IPS
 
Style Transfer (F32)
100% 3805
5.01 IPS
 
Style Transfer (F16)
100% 4520
5.95 IPS
 
Style Transfer (I8)
100% 4699
6.18 IPS
 
Image Super-Resolution (F32)
100% 957
34.2 IPS
 
Image Super-Resolution (F16)
100% 1133
40.4 IPS
 
Image Super-Resolution (I8)
100% 1000
35.7 IPS
 
Text Classification (F32)
100% 53
76.5 IPS
 
Text Classification (F16)
100% 200
287.8 IPS
 
Text Classification (I8)
96% 201
288.6 IPS
 
Machine Translation (F32)
100% 261
4.80 IPS
 
Machine Translation (F16)
100% 166
3.05 IPS
 
Machine Translation (I8)
99% 190
3.50 IPS
 

Compare

Set Baseline Geekbench 6 now available