Geekbench ML Score

718
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 09 2024 02:17 AM
Views 1

System Information

System Information
Operating System iOS 17.4.1
Model iPad mini (5th generation)
Model IDiPad11,1
Motherboard J210AP
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 2.85 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 334
62.5 IPS
 
Image Classification (F16)
100% 541
101.3 IPS
 
Image Classification (I8)
99% 540
101.0 IPS
 
Image Segmentation (F32)
100% 240
4.01 IPS
 
Image Segmentation (F16)
100% 282
4.72 IPS
 
Image Segmentation (I8)
100% 280
4.67 IPS
 
Pose Estimation (F32)
100% 837
1.01 IPS
 
Pose Estimation (F16)
100% 949
1.15 IPS
 
Pose Estimation (I8)
100% 971
1.18 IPS
 
Object Detection (F32)
100% 370
27.6 IPS
 
Object Detection (F16)
100% 626
46.7 IPS
 
Object Detection (I8)
97% 371
27.7 IPS
 
Face Detection (F32)
100% 768
9.13 IPS
 
Face Detection (F16)
97% 1362
16.2 IPS
 
Face Detection (I8)
96% 1451
17.3 IPS
 
Depth Estimation (F32)
100% 850
6.59 IPS
 
Depth Estimation (F16)
100% 1660
12.9 IPS
 
Depth Estimation (I8)
99% 1656
12.8 IPS
 
Style Transfer (F32)
100% 2264
2.98 IPS
 
Style Transfer (F16)
100% 4094
5.38 IPS
 
Style Transfer (I8)
100% 4348
5.72 IPS
 
Image Super-Resolution (F32)
100% 717
25.6 IPS
 
Image Super-Resolution (F16)
100% 964
34.4 IPS
 
Image Super-Resolution (I8)
100% 936
33.4 IPS
 
Text Classification (F32)
100% 264
379.4 IPS
 
Text Classification (F16)
100% 514
738.6 IPS
 
Text Classification (I8)
96% 514
739.4 IPS
 
Machine Translation (F32)
100% 363
6.69 IPS
 
Machine Translation (F16)
100% 489
8.99 IPS
 
Machine Translation (I8)
99% 353
6.50 IPS
 

Compare

Set Baseline Geekbench 6 now available