Geekbench ML Score

7341
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 08 2024 12:00 PM
Views 4

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% 3375
631.5 IPS
 
Image Classification (F16)
100% 6442
1.21 KIPS
 
Image Classification (I8)
99% 7059
1.32 KIPS
 
Image Segmentation (F32)
100% 1427
23.8 IPS
 
Image Segmentation (F16)
100% 1586
26.5 IPS
 
Image Segmentation (I8)
100% 1599
26.7 IPS
 
Pose Estimation (F32)
100% 23512
28.5 IPS
 
Pose Estimation (F16)
100% 82633
100.1 IPS
 
Pose Estimation (I8)
100% 84422
102.2 IPS
 
Object Detection (F32)
100% 2839
211.9 IPS
 
Object Detection (F16)
100% 3767
281.2 IPS
 
Object Detection (I8)
97% 2591
193.5 IPS
 
Face Detection (F32)
100% 9333
111.0 IPS
 
Face Detection (F16)
97% 10633
126.4 IPS
 
Face Detection (I8)
96% 10629
126.4 IPS
 
Depth Estimation (F32)
100% 16433
127.4 IPS
 
Depth Estimation (F16)
100% 37485
290.7 IPS
 
Depth Estimation (I8)
37% 36201
280.7 IPS
 
Style Transfer (F32)
100% 37339
49.1 IPS
 
Style Transfer (F16)
100% 130807
172.1 IPS
 
Style Transfer (I8)
100% 130058
171.1 IPS
 
Image Super-Resolution (F32)
100% 7694
274.8 IPS
 
Image Super-Resolution (F16)
100% 17997
642.7 IPS
 
Image Super-Resolution (I8)
100% 18403
657.2 IPS
 
Text Classification (F32)
100% 1100
1.58 KIPS
 
Text Classification (F16)
100% 749
1.08 KIPS
 
Text Classification (I8)
96% 743
1.07 KIPS
 
Machine Translation (F32)
100% 805
14.8 IPS
 
Machine Translation (F16)
100% 2633
48.5 IPS
 
Machine Translation (I8)
99% 756
13.9 IPS
 

Compare

Set Baseline Geekbench 6 now available