Geekbench ML Score

7301
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 09 2024 10:25 AM
Views 1

System Information

System Information
Operating System iOS 17.4.1
Model iPad Pro (11-inch, 4th generation)
Model IDiPad14,3
Motherboard J617AP
CPU Information
Name Apple M2
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.49 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 Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3350
626.8 IPS
 
Image Classification (F16)
100% 6455
1.21 KIPS
 
Image Classification (I8)
99% 7005
1.31 KIPS
 
Image Segmentation (F32)
100% 1451
24.2 IPS
 
Image Segmentation (F16)
100% 1592
26.6 IPS
 
Image Segmentation (I8)
100% 1587
26.5 IPS
 
Pose Estimation (F32)
100% 22579
27.3 IPS
 
Pose Estimation (F16)
100% 80948
98.0 IPS
 
Pose Estimation (I8)
100% 85276
103.3 IPS
 
Object Detection (F32)
100% 2794
208.6 IPS
 
Object Detection (F16)
100% 3668
273.8 IPS
 
Object Detection (I8)
97% 2607
194.6 IPS
 
Face Detection (F32)
100% 9296
110.5 IPS
 
Face Detection (F16)
97% 10639
126.5 IPS
 
Face Detection (I8)
96% 10674
126.9 IPS
 
Depth Estimation (F32)
100% 16025
124.3 IPS
 
Depth Estimation (F16)
100% 37316
289.4 IPS
 
Depth Estimation (I8)
37% 36130
280.2 IPS
 
Style Transfer (F32)
100% 39391
51.8 IPS
 
Style Transfer (F16)
100% 131677
173.2 IPS
 
Style Transfer (I8)
100% 132445
174.2 IPS
 
Image Super-Resolution (F32)
100% 7246
258.8 IPS
 
Image Super-Resolution (F16)
100% 17904
639.4 IPS
 
Image Super-Resolution (I8)
100% 18174
649.0 IPS
 
Text Classification (F32)
100% 1100
1.58 KIPS
 
Text Classification (F16)
100% 742
1.07 KIPS
 
Text Classification (I8)
96% 745
1.07 KIPS
 
Machine Translation (F32)
100% 797
14.7 IPS
 
Machine Translation (F16)
100% 2610
48.0 IPS
 
Machine Translation (I8)
99% 740
13.6 IPS
 

Compare

Set Baseline Geekbench 6 now available