Geekbench ML Score

1242
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date October 19 2024 03:46 AM
Views 1

System Information

System Information
Operating System iOS 16.3.1
Model iPhone XS
Model IDiPhone11,2
Motherboard D321AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
Cluster 12 Cores
Cluster 24 Cores
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 3.69 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 220
41.1 IPS
 
Image Classification (F16)
100% 2009
376.0 IPS
 
Image Classification (I8)
99% 1990
372.4 IPS
 
Image Segmentation (F32)
100% 215
3.59 IPS
 
Image Segmentation (F16)
100% 389
6.49 IPS
 
Image Segmentation (I8)
100% 388
6.47 IPS
 
Pose Estimation (F32)
100% 1746
2.11 IPS
 
Pose Estimation (F16)
100% 23184
28.1 IPS
 
Pose Estimation (I8)
100% 24072
29.1 IPS
 
Object Detection (F32)
100% 436
32.6 IPS
 
Object Detection (F16)
100% 444
33.1 IPS
 
Object Detection (I8)
97% 396
29.5 IPS
 
Face Detection (F32)
100% 1936
23.0 IPS
 
Face Detection (F16)
97% 2220
26.4 IPS
 
Face Detection (I8)
96% 2166
25.8 IPS
 
Depth Estimation (F32)
100% 1862
14.4 IPS
 
Depth Estimation (F16)
100% 18684
144.9 IPS
 
Depth Estimation (I8)
99% 17707
137.3 IPS
 
Style Transfer (F32)
24% 4726
6.22 IPS
 
Style Transfer (F16)
30% 5540
7.29 IPS
 
Style Transfer (I8)
30% 4943
6.50 IPS
 
Image Super-Resolution (F32)
100% 743
26.5 IPS
 
Image Super-Resolution (F16)
100% 3230
115.4 IPS
 
Image Super-Resolution (I8)
100% 3213
114.7 IPS
 
Text Classification (F32)
100% 168
241.0 IPS
 
Text Classification (F16)
100% 206
295.4 IPS
 
Text Classification (I8)
96% 209
299.7 IPS
 
Machine Translation (F32)
100% 196
3.60 IPS
 
Machine Translation (F16)
100% 204
3.75 IPS
 
Machine Translation (I8)
99% 193
3.54 IPS
 

Compare

Set Baseline Geekbench 6 now available