Geekbench ML Score

10079
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date September 20 2024 07:12 AM
Views 1

System Information

System Information
Operating System iOS 18.0
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 7.37 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3374
631.3 IPS
 
Image Classification (F16)
100% 11083
2.07 KIPS
 
Image Classification (I8)
99% 12014
2.25 KIPS
 
Image Segmentation (F32)
100% 1453
24.3 IPS
 
Image Segmentation (F16)
100% 1859
31.0 IPS
 
Image Segmentation (I8)
100% 1853
31.0 IPS
 
Pose Estimation (F32)
100% 23520
28.5 IPS
 
Pose Estimation (F16)
100% 94125
114.0 IPS
 
Pose Estimation (I8)
100% 96242
116.5 IPS
 
Object Detection (F32)
100% 2880
215.0 IPS
 
Object Detection (F16)
100% 5038
376.2 IPS
 
Object Detection (I8)
97% 2656
198.3 IPS
 
Face Detection (F32)
100% 8852
105.2 IPS
 
Face Detection (F16)
97% 19038
226.4 IPS
 
Face Detection (I8)
96% 19353
230.1 IPS
 
Depth Estimation (F32)
100% 16185
125.5 IPS
 
Depth Estimation (F16)
100% 54033
419.0 IPS
 
Depth Estimation (I8)
37% 53037
411.3 IPS
 
Style Transfer (F32)
100% 41539
54.6 IPS
 
Style Transfer (F16)
100% 149492
196.6 IPS
 
Style Transfer (I8)
100% 148915
195.9 IPS
 
Image Super-Resolution (F32)
100% 9723
347.2 IPS
 
Image Super-Resolution (F16)
100% 34525
1.23 KIPS
 
Image Super-Resolution (I8)
100% 33387
1.19 KIPS
 
Text Classification (F32)
100% 2030
2.92 KIPS
 
Text Classification (F16)
100% 3348
4.81 KIPS
 
Text Classification (I8)
96% 3411
4.90 KIPS
 
Machine Translation (F32)
100% 864
15.9 IPS
 
Machine Translation (F16)
100% 2749
50.6 IPS
 
Machine Translation (I8)
99% 796
14.6 IPS
 

Compare

Set Baseline Geekbench 6 now available