Geekbench ML Score

3522
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date December 09 2024 02:23 PM
Views 2

System Information

System Information
Operating System iOS 18.1.1
Model iPad13,17
Model IDiPad13,17
Motherboard J408AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.19 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 7.47 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1374
257.2 IPS
 
Image Classification (F16)
100% 2144
401.2 IPS
 
Image Classification (I8)
99% 2144
401.2 IPS
 
Image Segmentation (F32)
100% 641
10.7 IPS
 
Image Segmentation (F16)
100% 765
12.8 IPS
 
Image Segmentation (I8)
100% 768
12.8 IPS
 
Pose Estimation (F32)
100% 6313
7.64 IPS
 
Pose Estimation (F16)
100% 13365
16.2 IPS
 
Pose Estimation (I8)
100% 13343
16.2 IPS
 
Object Detection (F32)
100% 1355
101.2 IPS
 
Object Detection (F16)
100% 1986
148.3 IPS
 
Object Detection (I8)
97% 1354
101.1 IPS
 
Face Detection (F32)
100% 2996
35.6 IPS
 
Face Detection (F16)
97% 5436
64.6 IPS
 
Face Detection (I8)
97% 5442
64.7 IPS
 
Depth Estimation (F32)
100% 5751
44.6 IPS
 
Depth Estimation (F16)
100% 11036
85.6 IPS
 
Depth Estimation (I8)
99% 11031
85.5 IPS
 
Style Transfer (F32)
100% 16767
22.1 IPS
 
Style Transfer (F16)
100% 25804
33.9 IPS
 
Style Transfer (I8)
100% 25808
33.9 IPS
 
Image Super-Resolution (F32)
100% 3873
138.3 IPS
 
Image Super-Resolution (F16)
100% 4593
164.0 IPS
 
Image Super-Resolution (I8)
100% 4671
166.8 IPS
 
Text Classification (F32)
100% 2100
3.02 KIPS
 
Text Classification (F16)
100% 3551
5.10 KIPS
 
Text Classification (I8)
96% 3574
5.14 KIPS
 
Machine Translation (F32)
100% 1109
20.4 IPS
 
Machine Translation (F16)
100% 1382
25.4 IPS
 
Machine Translation (I8)
99% 1109
20.4 IPS
 

Compare

Set Baseline Geekbench 6 now available