Geekbench ML Score

2000
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date June 29 2024 04:12 AM
Views 1

System Information

System Information
Operating System iOS 17.5.1
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 GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 565
105.8 IPS
 
Image Classification (F16)
100% 611
114.4 IPS
 
Image Classification (I8)
99% 541
101.2 IPS
 
Image Segmentation (F32)
100% 1046
17.5 IPS
 
Image Segmentation (F16)
100% 1150
19.2 IPS
 
Image Segmentation (I8)
100% 1048
17.5 IPS
 
Pose Estimation (F32)
100% 10309
12.5 IPS
 
Pose Estimation (F16)
100% 10998
13.3 IPS
 
Pose Estimation (I8)
100% 11013
13.3 IPS
 
Object Detection (F32)
100% 752
56.1 IPS
 
Object Detection (F16)
100% 791
59.1 IPS
 
Object Detection (I8)
97% 839
62.6 IPS
 
Face Detection (F32)
100% 3594
42.7 IPS
 
Face Detection (F16)
98% 3820
45.4 IPS
 
Face Detection (I8)
97% 3563
42.4 IPS
 
Depth Estimation (F32)
100% 6443
50.0 IPS
 
Depth Estimation (F16)
100% 6868
53.3 IPS
 
Depth Estimation (I8)
37% 6763
52.4 IPS
 
Style Transfer (F32)
100% 18162
23.9 IPS
 
Style Transfer (F16)
100% 22471
29.6 IPS
 
Style Transfer (I8)
100% 22468
29.6 IPS
 
Image Super-Resolution (F32)
100% 2762
98.6 IPS
 
Image Super-Resolution (F16)
100% 2833
101.2 IPS
 
Image Super-Resolution (I8)
100% 2783
99.4 IPS
 
Text Classification (F32)
100% 359
515.3 IPS
 
Text Classification (F16)
100% 360
518.0 IPS
 
Text Classification (I8)
96% 230
329.9 IPS
 
Machine Translation (F32)
100% 448
8.24 IPS
 
Machine Translation (F16)
100% 468
8.61 IPS
 
Machine Translation (I8)
99% 407
7.50 IPS
 

Compare

Set Baseline Geekbench 6 now available