Geekbench ML Score

3145
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 08 2024 06:15 PM
Views 1

System Information

System Information
Operating System iOS 17.4.1
Model iPad mini (6th generation)
Model IDiPad14,1
Motherboard J310AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.92 GHz
Cluster 12 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 3.78 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1324
247.8 IPS
 
Image Classification (F16)
100% 1664
311.3 IPS
 
Image Classification (I8)
99% 1666
311.7 IPS
 
Image Segmentation (F32)
100% 764
12.8 IPS
 
Image Segmentation (F16)
100% 745
12.4 IPS
 
Image Segmentation (I8)
100% 762
12.7 IPS
 
Pose Estimation (F32)
100% 5157
6.24 IPS
 
Pose Estimation (F16)
100% 12270
14.9 IPS
 
Pose Estimation (I8)
100% 12460
15.1 IPS
 
Object Detection (F32)
100% 1286
96.0 IPS
 
Object Detection (F16)
100% 1729
129.1 IPS
 
Object Detection (I8)
97% 1241
92.7 IPS
 
Face Detection (F32)
100% 2337
27.8 IPS
 
Face Detection (F16)
97% 3705
44.1 IPS
 
Face Detection (I8)
97% 3759
44.7 IPS
 
Depth Estimation (F32)
100% 4827
37.4 IPS
 
Depth Estimation (F16)
100% 7776
60.3 IPS
 
Depth Estimation (I8)
99% 7762
60.2 IPS
 
Style Transfer (F32)
100% 15583
20.5 IPS
 
Style Transfer (F16)
100% 23978
31.5 IPS
 
Style Transfer (I8)
100% 24013
31.6 IPS
 
Image Super-Resolution (F32)
100% 3623
129.4 IPS
 
Image Super-Resolution (F16)
100% 4824
172.3 IPS
 
Image Super-Resolution (I8)
100% 4842
172.9 IPS
 
Text Classification (F32)
100% 2168
3.12 KIPS
 
Text Classification (F16)
100% 3567
5.13 KIPS
 
Text Classification (I8)
96% 3513
5.05 KIPS
 
Machine Translation (F32)
100% 923
17.0 IPS
 
Machine Translation (F16)
100% 1267
23.3 IPS
 
Machine Translation (I8)
99% 1078
19.8 IPS
 

Compare

Set Baseline Geekbench 6 now available