Geekbench ML Score

5167
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 11 2024 03:09 PM
Views 7

System Information

System Information
Operating System iOS 17.5
Model iPad14,6
Model IDiPad14,6
Motherboard J621AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.49 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 15.31 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3302
617.8 IPS
 
Image Classification (F16)
100% 3442
644.0 IPS
 
Image Classification (I8)
99% 2992
559.8 IPS
 
Image Segmentation (F32)
100% 1430
23.9 IPS
 
Image Segmentation (F16)
100% 1517
25.3 IPS
 
Image Segmentation (I8)
100% 1516
25.3 IPS
 
Pose Estimation (F32)
100% 22641
27.4 IPS
 
Pose Estimation (F16)
100% 24988
30.3 IPS
 
Pose Estimation (I8)
100% 24570
29.8 IPS
 
Object Detection (F32)
100% 2818
210.4 IPS
 
Object Detection (F16)
100% 2831
211.4 IPS
 
Object Detection (I8)
97% 2586
193.0 IPS
 
Face Detection (F32)
100% 9287
110.4 IPS
 
Face Detection (F16)
98% 10562
125.6 IPS
 
Face Detection (I8)
97% 10151
120.7 IPS
 
Depth Estimation (F32)
100% 15992
124.0 IPS
 
Depth Estimation (F16)
100% 17390
134.9 IPS
 
Depth Estimation (I8)
37% 16170
125.4 IPS
 
Style Transfer (F32)
100% 39420
51.9 IPS
 
Style Transfer (F16)
100% 47023
61.9 IPS
 
Style Transfer (I8)
100% 42742
56.2 IPS
 
Image Super-Resolution (F32)
100% 7757
277.0 IPS
 
Image Super-Resolution (F16)
100% 10091
360.4 IPS
 
Image Super-Resolution (I8)
100% 9860
352.1 IPS
 
Text Classification (F32)
100% 1112
1.60 KIPS
 
Text Classification (F16)
100% 732
1.05 KIPS
 
Text Classification (I8)
96% 731
1.05 KIPS
 
Machine Translation (F32)
100% 790
14.5 IPS
 
Machine Translation (F16)
100% 801
14.7 IPS
 
Machine Translation (I8)
99% 759
14.0 IPS
 

Compare

Set Baseline Geekbench 6 now available