Geekbench ML Score

637
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date February 14 2025 06:06 PM
Views 4

System Information

System Information
Operating System iOS 16.7.10
Model iPhone 8 Plus
Model IDiPhone10,5
Motherboard D211AP
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 2.90 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 180
33.7 IPS
 
Image Classification (F16)
100% 144
26.9 IPS
 
Image Classification (I8)
99% 160
29.9 IPS
 
Image Segmentation (F32)
100% 187
3.12 IPS
 
Image Segmentation (F16)
100% 199
3.32 IPS
 
Image Segmentation (I8)
100% 200
3.35 IPS
 
Pose Estimation (F32)
100% 2376
2.88 IPS
 
Pose Estimation (F16)
100% 2723
3.30 IPS
 
Pose Estimation (I8)
100% 2646
3.20 IPS
 
Object Detection (F32)
100% 323
24.1 IPS
 
Object Detection (F16)
100% 281
21.0 IPS
 
Object Detection (I8)
97% 321
24.0 IPS
 
Face Detection (F32)
100% 1016
12.1 IPS
 
Face Detection (F16)
100% 971
11.5 IPS
 
Face Detection (I8)
99% 1018
12.1 IPS
 
Depth Estimation (F32)
100% 2325
18.0 IPS
 
Depth Estimation (F16)
100% 2301
17.8 IPS
 
Depth Estimation (I8)
99% 2308
17.9 IPS
 
Style Transfer (F32)
100% 4389
5.77 IPS
 
Style Transfer (F16)
100% 4942
6.50 IPS
 
Style Transfer (I8)
100% 4925
6.48 IPS
 
Image Super-Resolution (F32)
100% 1113
39.8 IPS
 
Image Super-Resolution (F16)
100% 1065
38.0 IPS
 
Image Super-Resolution (I8)
100% 1126
40.2 IPS
 
Text Classification (F32)
100% 60
85.8 IPS
 
Text Classification (F16)
100% 189
272.0 IPS
 
Text Classification (I8)
96% 180
259.3 IPS
 
Machine Translation (F32)
100% 314
5.77 IPS
 
Machine Translation (F16)
100% 246
4.53 IPS
 
Machine Translation (I8)
99% 316
5.81 IPS
 

Compare

Set Baseline Geekbench 6 now available