Geekbench ML Score

1953
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 09 2024 10:04 AM
Views 1

System Information

System Information
Operating System iOS 17.2
Model iPad Pro (11-inch 3rd generation)
Model IDiPad13,4
Motherboard J517AP
CPU Information
Name Apple M1
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 7.35 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1072
200.7 IPS
 
Image Classification (F16)
100% 972
182.0 IPS
 
Image Classification (I8)
99% 976
182.7 IPS
 
Image Segmentation (F32)
100% 448
7.48 IPS
 
Image Segmentation (F16)
100% 414
6.92 IPS
 
Image Segmentation (I8)
100% 414
6.91 IPS
 
Pose Estimation (F32)
100% 5549
6.72 IPS
 
Pose Estimation (F16)
100% 11108
13.5 IPS
 
Pose Estimation (I8)
100% 11135
13.5 IPS
 
Object Detection (F32)
100% 1106
82.6 IPS
 
Object Detection (F16)
100% 1078
80.5 IPS
 
Object Detection (I8)
97% 1104
82.4 IPS
 
Face Detection (F32)
100% 2180
25.9 IPS
 
Face Detection (F16)
100% 1817
21.6 IPS
 
Face Detection (I8)
99% 1824
21.7 IPS
 
Depth Estimation (F32)
100% 3845
29.8 IPS
 
Depth Estimation (F16)
99% 4108
31.9 IPS
 
Depth Estimation (I8)
99% 4113
31.9 IPS
 
Style Transfer (F32)
100% 10545
13.9 IPS
 
Style Transfer (F16)
100% 12585
16.6 IPS
 
Style Transfer (I8)
100% 12610
16.6 IPS
 
Image Super-Resolution (F32)
100% 2908
103.8 IPS
 
Image Super-Resolution (F16)
100% 2747
98.1 IPS
 
Image Super-Resolution (I8)
100% 2750
98.2 IPS
 
Text Classification (F32)
100% 1180
1.70 KIPS
 
Text Classification (F16)
100% 766
1.10 KIPS
 
Text Classification (I8)
96% 766
1.10 KIPS
 
Machine Translation (F32)
100% 817
15.0 IPS
 
Machine Translation (F16)
99% 937
17.2 IPS
 
Machine Translation (I8)
99% 818
15.0 IPS
 

Compare

Set Baseline Geekbench 6 now available