Geekbench ML Score

609
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date April 10 2025 06:23 AM
Views 7

System Information

System Information
Operating System iOS 16.7.10
Model iPad Pro (12.9-inch)
Model IDiPad6,8
Motherboard J99aAP
CPU Information
Name Apple A9X
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.26 GHz
Cluster 12 Cores
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 3.90 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 325
60.9 IPS
 
Image Classification (F16)
100% 261
48.8 IPS
 
Image Classification (I8)
99% 251
46.9 IPS
 
Image Segmentation (F32)
100% 188
3.15 IPS
 
Image Segmentation (F16)
100% 186
3.11 IPS
 
Image Segmentation (I8)
100% 186
3.10 IPS
 
Pose Estimation (F32)
100% 2005
2.43 IPS
 
Pose Estimation (F16)
100% 1992
2.41 IPS
 
Pose Estimation (I8)
100% 1983
2.40 IPS
 
Object Detection (F32)
100% 312
23.3 IPS
 
Object Detection (F16)
100% 278
20.8 IPS
 
Object Detection (I8)
97% 324
24.2 IPS
 
Face Detection (F32)
100% 1365
16.2 IPS
 
Face Detection (F16)
100% 1340
15.9 IPS
 
Face Detection (I8)
99% 1325
15.8 IPS
 
Depth Estimation (F32)
100% 2105
16.3 IPS
 
Depth Estimation (F16)
100% 2114
16.4 IPS
 
Depth Estimation (I8)
99% 2215
17.2 IPS
 
Style Transfer (F32)
100% 4905
6.45 IPS
 
Style Transfer (F16)
100% 4574
6.02 IPS
 
Style Transfer (I8)
100% 4684
6.16 IPS
 
Image Super-Resolution (F32)
100% 1026
36.6 IPS
 
Image Super-Resolution (F16)
100% 1101
39.3 IPS
 
Image Super-Resolution (I8)
100% 1025
36.6 IPS
 
Text Classification (F32)
100% 45
64.2 IPS
 
Text Classification (F16)
100% 101
144.9 IPS
 
Text Classification (I8)
96% 116
166.5 IPS
 
Machine Translation (F32)
100% 208
3.82 IPS
 
Machine Translation (F16)
100% 176
3.25 IPS
 
Machine Translation (I8)
99% 209
3.85 IPS
 

Compare

Set Baseline Geekbench 6 now available