Geekbench ML Score

4702
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 15 2024 03:20 PM
Views 1

System Information

System Information
Operating System iOS 17.5.1
Model iPad16,6
Model IDiPad16,6
Motherboard J721AP
CPU Information
Name ARM
Topology 1 Processor, 10 Cores
Identifier ARM
Base Frequency 4.41 GHz
Cluster 14 Cores
Cluster 26 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 15.05 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1915
358.3 IPS
 
Image Classification (F16)
100% 2554
477.9 IPS
 
Image Classification (I8)
99% 2559
478.9 IPS
 
Image Segmentation (F32)
100% 1192
19.9 IPS
 
Image Segmentation (F16)
100% 1166
19.5 IPS
 
Image Segmentation (I8)
100% 1183
19.8 IPS
 
Pose Estimation (F32)
100% 9470
11.5 IPS
 
Pose Estimation (F16)
100% 17916
21.7 IPS
 
Pose Estimation (I8)
100% 17953
21.7 IPS
 
Object Detection (F32)
100% 1958
146.2 IPS
 
Object Detection (F16)
100% 2673
199.5 IPS
 
Object Detection (I8)
97% 1949
145.5 IPS
 
Face Detection (F32)
100% 3561
42.3 IPS
 
Face Detection (F16)
97% 5647
67.1 IPS
 
Face Detection (I8)
97% 5641
67.1 IPS
 
Depth Estimation (F32)
100% 7619
59.1 IPS
 
Depth Estimation (F16)
100% 11301
87.6 IPS
 
Depth Estimation (I8)
99% 11300
87.6 IPS
 
Style Transfer (F32)
100% 23519
30.9 IPS
 
Style Transfer (F16)
100% 35096
46.2 IPS
 
Style Transfer (I8)
100% 35005
46.0 IPS
 
Image Super-Resolution (F32)
100% 5787
206.7 IPS
 
Image Super-Resolution (F16)
100% 6812
243.3 IPS
 
Image Super-Resolution (I8)
100% 6827
243.8 IPS
 
Text Classification (F32)
100% 2738
3.93 KIPS
 
Text Classification (F16)
100% 4383
6.30 KIPS
 
Text Classification (I8)
96% 4427
6.36 KIPS
 
Machine Translation (F32)
100% 1648
30.3 IPS
 
Machine Translation (F16)
100% 1891
34.8 IPS
 
Machine Translation (I8)
99% 1630
30.0 IPS
 

Compare

Set Baseline Geekbench 6 now available