Geekbench ML Score

601
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date February 06 2025 10:00 AM
Views 4

System Information

System Information
Operating System iOS 16.7.10
Model iPad Pro (12.9-inch)
Model IDiPad6,7
Motherboard J98aAP
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 GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 227
42.5 IPS
 
Image Classification (F16)
100% 230
43.0 IPS
 
Image Classification (I8)
99% 245
45.8 IPS
 
Image Segmentation (F32)
100% 187
3.13 IPS
 
Image Segmentation (F16)
100% 188
3.14 IPS
 
Image Segmentation (I8)
100% 186
3.10 IPS
 
Pose Estimation (F32)
100% 1994
2.41 IPS
 
Pose Estimation (F16)
100% 1960
2.37 IPS
 
Pose Estimation (I8)
100% 1961
2.37 IPS
 
Object Detection (F32)
100% 299
22.4 IPS
 
Object Detection (F16)
100% 282
21.1 IPS
 
Object Detection (I8)
97% 402
30.0 IPS
 
Face Detection (F32)
100% 1384
16.5 IPS
 
Face Detection (F16)
100% 1330
15.8 IPS
 
Face Detection (I8)
99% 1309
15.6 IPS
 
Depth Estimation (F32)
100% 2054
15.9 IPS
 
Depth Estimation (F16)
100% 2040
15.8 IPS
 
Depth Estimation (I8)
99% 2124
16.5 IPS
 
Style Transfer (F32)
100% 4830
6.35 IPS
 
Style Transfer (F16)
100% 4667
6.14 IPS
 
Style Transfer (I8)
100% 4679
6.15 IPS
 
Image Super-Resolution (F32)
100% 1147
41.0 IPS
 
Image Super-Resolution (F16)
100% 1093
39.0 IPS
 
Image Super-Resolution (I8)
100% 1141
40.8 IPS
 
Text Classification (F32)
100% 45
64.2 IPS
 
Text Classification (F16)
100% 100
144.4 IPS
 
Text Classification (I8)
96% 100
144.1 IPS
 
Machine Translation (F32)
100% 208
3.83 IPS
 
Machine Translation (F16)
100% 176
3.24 IPS
 
Machine Translation (I8)
99% 209
3.85 IPS
 

Compare

Set Baseline Geekbench 6 now available