Geekbench ML Score

714
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 22 2024 11:20 AM
Views 1

System Information

System Information
Operating System iOS 17.6.1
Model iPad mini (5th generation)
Model IDiPad11,2
Motherboard J211AP
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% 316
59.1 IPS
 
Image Classification (F16)
100% 546
102.3 IPS
 
Image Classification (I8)
99% 542
101.4 IPS
 
Image Segmentation (F32)
100% 229
3.82 IPS
 
Image Segmentation (F16)
100% 291
4.86 IPS
 
Image Segmentation (I8)
100% 286
4.78 IPS
 
Pose Estimation (F32)
100% 1110
1.34 IPS
 
Pose Estimation (F16)
100% 806
0.98 IPS
 
Pose Estimation (I8)
100% 822
1.00 IPS
 
Object Detection (F32)
100% 347
25.9 IPS
 
Object Detection (F16)
100% 610
45.5 IPS
 
Object Detection (I8)
97% 344
25.6 IPS
 
Face Detection (F32)
100% 720
8.56 IPS
 
Face Detection (F16)
97% 1417
16.8 IPS
 
Face Detection (I8)
96% 1458
17.3 IPS
 
Depth Estimation (F32)
100% 887
6.88 IPS
 
Depth Estimation (F16)
100% 1594
12.4 IPS
 
Depth Estimation (I8)
99% 1626
12.6 IPS
 
Style Transfer (F32)
100% 2349
3.09 IPS
 
Style Transfer (F16)
100% 4068
5.35 IPS
 
Style Transfer (I8)
100% 3633
4.78 IPS
 
Image Super-Resolution (F32)
100% 748
26.7 IPS
 
Image Super-Resolution (F16)
100% 913
32.6 IPS
 
Image Super-Resolution (I8)
100% 915
32.7 IPS
 
Text Classification (F32)
100% 271
388.9 IPS
 
Text Classification (F16)
100% 521
749.1 IPS
 
Text Classification (I8)
96% 528
758.9 IPS
 
Machine Translation (F32)
100% 388
7.15 IPS
 
Machine Translation (F16)
100% 544
10.0 IPS
 
Machine Translation (I8)
99% 371
6.83 IPS
 

Compare

Set Baseline Geekbench 6 now available