Geekbench ML Score

2992
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 15 2024 01:12 PM
Views 1

System Information

System Information
Operating System iOS 17.6.1
Model iPad Pro (12.9-inch 5th generation)
Model IDiPad13,8
Motherboard J522AP
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 7.31 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1294
242.1 IPS
 
Image Classification (F16)
100% 1660
310.7 IPS
 
Image Classification (I8)
99% 1664
311.4 IPS
 
Image Segmentation (F32)
100% 601
10.0 IPS
 
Image Segmentation (F16)
100% 594
9.92 IPS
 
Image Segmentation (I8)
100% 590
9.85 IPS
 
Pose Estimation (F32)
100% 5619
6.80 IPS
 
Pose Estimation (F16)
100% 12929
15.7 IPS
 
Pose Estimation (I8)
100% 12958
15.7 IPS
 
Object Detection (F32)
100% 1279
95.5 IPS
 
Object Detection (F16)
100% 1731
129.2 IPS
 
Object Detection (I8)
97% 1301
97.1 IPS
 
Face Detection (F32)
100% 2368
28.2 IPS
 
Face Detection (F16)
97% 3984
47.4 IPS
 
Face Detection (I8)
97% 3982
47.3 IPS
 
Depth Estimation (F32)
100% 5178
40.2 IPS
 
Depth Estimation (F16)
100% 8117
62.9 IPS
 
Depth Estimation (I8)
99% 8115
62.9 IPS
 
Style Transfer (F32)
100% 15591
20.5 IPS
 
Style Transfer (F16)
100% 24381
32.1 IPS
 
Style Transfer (I8)
100% 24261
31.9 IPS
 
Image Super-Resolution (F32)
100% 3504
125.1 IPS
 
Image Super-Resolution (F16)
100% 4555
162.7 IPS
 
Image Super-Resolution (I8)
100% 4568
163.2 IPS
 
Text Classification (F32)
100% 2104
3.02 KIPS
 
Text Classification (F16)
100% 3437
4.94 KIPS
 
Text Classification (I8)
96% 3371
4.85 KIPS
 
Machine Translation (F32)
100% 716
13.2 IPS
 
Machine Translation (F16)
100% 857
15.8 IPS
 
Machine Translation (I8)
99% 724
13.3 IPS
 

Compare

Set Baseline Geekbench 6 now available