Geekbench ML Score

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

Result Information

Upload Date May 08 2024 01:07 PM
Views 1

System Information

System Information
Operating System iOS 17.4.1
Model iPad Pro (12.9-inch 5th generation)
Model IDiPad13,11
Motherboard J523xAP
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 15.31 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1280
239.5 IPS
 
Image Classification (F16)
100% 1662
310.9 IPS
 
Image Classification (I8)
99% 1671
312.7 IPS
 
Image Segmentation (F32)
100% 589
9.84 IPS
 
Image Segmentation (F16)
100% 590
9.85 IPS
 
Image Segmentation (I8)
100% 591
9.87 IPS
 
Pose Estimation (F32)
100% 5624
6.81 IPS
 
Pose Estimation (F16)
100% 12922
15.6 IPS
 
Pose Estimation (I8)
100% 12939
15.7 IPS
 
Object Detection (F32)
100% 1296
96.8 IPS
 
Object Detection (F16)
100% 1729
129.1 IPS
 
Object Detection (I8)
97% 1296
96.8 IPS
 
Face Detection (F32)
100% 2358
28.0 IPS
 
Face Detection (F16)
97% 3990
47.4 IPS
 
Face Detection (I8)
97% 3986
47.4 IPS
 
Depth Estimation (F32)
100% 5196
40.3 IPS
 
Depth Estimation (F16)
100% 8149
63.2 IPS
 
Depth Estimation (I8)
99% 8139
63.1 IPS
 
Style Transfer (F32)
100% 15602
20.5 IPS
 
Style Transfer (F16)
100% 24324
32.0 IPS
 
Style Transfer (I8)
100% 24464
32.2 IPS
 
Image Super-Resolution (F32)
100% 3472
124.0 IPS
 
Image Super-Resolution (F16)
100% 4511
161.1 IPS
 
Image Super-Resolution (I8)
100% 4513
161.2 IPS
 
Text Classification (F32)
100% 2106
3.03 KIPS
 
Text Classification (F16)
100% 3421
4.92 KIPS
 
Text Classification (I8)
96% 3407
4.90 KIPS
 
Machine Translation (F32)
100% 728
13.4 IPS
 
Machine Translation (F16)
100% 864
15.9 IPS
 
Machine Translation (I8)
99% 729
13.4 IPS
 

Compare

Set Baseline Geekbench 6 now available