Geekbench ML Score

1419
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date February 12 2024 05:17 PM
Views 1

System Information

System Information
Operating System iOS 17.3.1
Model iPhone 11
Model IDiPhone12,1
Motherboard N104AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
Cluster 12 Cores
Cluster 24 Cores
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.76 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 270
50.5 IPS
 
Image Classification (F16)
100% 1734
324.5 IPS
 
Image Classification (I8)
99% 1773
331.9 IPS
 
Image Segmentation (F32)
100% 184
3.07 IPS
 
Image Segmentation (F16)
100% 229
3.82 IPS
 
Image Segmentation (I8)
100% 230
3.84 IPS
 
Pose Estimation (F32)
100% 1711
2.07 IPS
 
Pose Estimation (F16)
100% 19534
23.7 IPS
 
Pose Estimation (I8)
100% 15349
18.6 IPS
 
Object Detection (F32)
100% 465
34.7 IPS
 
Object Detection (F16)
100% 925
69.1 IPS
 
Object Detection (I8)
97% 513
38.3 IPS
 
Face Detection (F32)
100% 2124
25.3 IPS
 
Face Detection (F16)
97% 4864
57.8 IPS
 
Face Detection (I8)
96% 4643
55.2 IPS
 
Depth Estimation (F32)
100% 2157
16.7 IPS
 
Depth Estimation (F16)
100% 18144
140.7 IPS
 
Depth Estimation (I8)
99% 18291
141.8 IPS
 
Style Transfer (F32)
24% 4551
5.99 IPS
 
Style Transfer (F16)
100% 16717
22.0 IPS
 
Style Transfer (I8)
100% 11242
14.8 IPS
 
Image Super-Resolution (F32)
100% 1000
35.7 IPS
 
Image Super-Resolution (F16)
100% 3544
126.6 IPS
 
Image Super-Resolution (I8)
100% 3361
120.0 IPS
 
Text Classification (F32)
100% 229
328.4 IPS
 
Text Classification (F16)
100% 275
395.3 IPS
 
Text Classification (I8)
96% 246
353.2 IPS
 
Machine Translation (F32)
100% 197
3.63 IPS
 
Machine Translation (F16)
100% 195
3.59 IPS
 
Machine Translation (I8)
99% 195
3.59 IPS
 

Compare

Set Baseline Geekbench 6 now available