Geekbench ML Score

3002
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 15 2024 04:00 PM
Views 1

System Information

System Information
Operating System iOS 17.6.1
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 7.33 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% 1679
314.2 IPS
 
Image Classification (I8)
99% 1676
313.7 IPS
 
Image Segmentation (F32)
100% 596
9.95 IPS
 
Image Segmentation (F16)
100% 595
9.93 IPS
 
Image Segmentation (I8)
100% 594
9.92 IPS
 
Pose Estimation (F32)
100% 5634
6.82 IPS
 
Pose Estimation (F16)
100% 12963
15.7 IPS
 
Pose Estimation (I8)
100% 12958
15.7 IPS
 
Object Detection (F32)
100% 1278
95.4 IPS
 
Object Detection (F16)
100% 1749
130.6 IPS
 
Object Detection (I8)
97% 1267
94.6 IPS
 
Face Detection (F32)
100% 2400
28.5 IPS
 
Face Detection (F16)
97% 4034
48.0 IPS
 
Face Detection (I8)
97% 4028
47.9 IPS
 
Depth Estimation (F32)
100% 5178
40.2 IPS
 
Depth Estimation (F16)
100% 8161
63.3 IPS
 
Depth Estimation (I8)
99% 8171
63.4 IPS
 
Style Transfer (F32)
100% 15654
20.6 IPS
 
Style Transfer (F16)
100% 24365
32.1 IPS
 
Style Transfer (I8)
100% 24354
32.0 IPS
 
Image Super-Resolution (F32)
100% 3506
125.2 IPS
 
Image Super-Resolution (F16)
100% 4579
163.5 IPS
 
Image Super-Resolution (I8)
100% 4508
161.0 IPS
 
Text Classification (F32)
100% 2111
3.03 KIPS
 
Text Classification (F16)
100% 3390
4.87 KIPS
 
Text Classification (I8)
96% 3417
4.91 KIPS
 
Machine Translation (F32)
100% 733
13.5 IPS
 
Machine Translation (F16)
100% 868
16.0 IPS
 
Machine Translation (I8)
99% 728
13.4 IPS
 

Compare

Set Baseline Geekbench 6 now available