Geekbench ML Score

6022
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date June 11 2024 07:09 PM
Views 1

System Information

System Information
Operating System iOS 18.0
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 15.35 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3314
620.1 IPS
 
Image Classification (F16)
100% 3577
669.4 IPS
 
Image Classification (I8)
99% 3160
591.3 IPS
 
Image Segmentation (F32)
100% 1433
23.9 IPS
 
Image Segmentation (F16)
100% 1514
25.3 IPS
 
Image Segmentation (I8)
100% 1505
25.1 IPS
 
Pose Estimation (F32)
100% 23473
28.4 IPS
 
Pose Estimation (F16)
100% 25349
30.7 IPS
 
Pose Estimation (I8)
100% 24559
29.7 IPS
 
Object Detection (F32)
100% 2853
213.0 IPS
 
Object Detection (F16)
100% 2991
223.3 IPS
 
Object Detection (I8)
97% 2642
197.2 IPS
 
Face Detection (F32)
100% 8947
106.4 IPS
 
Face Detection (F16)
98% 11272
134.0 IPS
 
Face Detection (I8)
97% 10891
129.5 IPS
 
Depth Estimation (F32)
100% 16241
125.9 IPS
 
Depth Estimation (F16)
100% 17631
136.7 IPS
 
Depth Estimation (I8)
99% 16072
124.6 IPS
 
Style Transfer (F32)
100% 37946
49.9 IPS
 
Style Transfer (F16)
100% 46603
61.3 IPS
 
Style Transfer (I8)
100% 46377
61.0 IPS
 
Image Super-Resolution (F32)
100% 9776
349.1 IPS
 
Image Super-Resolution (F16)
100% 10226
365.2 IPS
 
Image Super-Resolution (I8)
100% 9588
342.4 IPS
 
Text Classification (F32)
100% 2082
2.99 KIPS
 
Text Classification (F16)
100% 3410
4.90 KIPS
 
Text Classification (I8)
96% 3393
4.88 KIPS
 
Machine Translation (F32)
100% 882
16.2 IPS
 
Machine Translation (F16)
100% 865
15.9 IPS
 
Machine Translation (I8)
99% 841
15.5 IPS
 

Compare

Set Baseline Geekbench 6 now available