Geekbench ML Score

282
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date October 14 2024 10:23 AM
Views 1

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 CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 146
27.4 IPS
 
Image Classification (F16)
100% 129
24.2 IPS
 
Image Classification (I8)
99% 129
24.0 IPS
 
Image Segmentation (F32)
100% 123
2.05 IPS
 
Image Segmentation (F16)
100% 123
2.05 IPS
 
Image Segmentation (I8)
100% 123
2.06 IPS
 
Pose Estimation (F32)
100% 859
1.04 IPS
 
Pose Estimation (F16)
100% 851
1.03 IPS
 
Pose Estimation (I8)
100% 859
1.04 IPS
 
Object Detection (F32)
100% 159
11.9 IPS
 
Object Detection (F16)
100% 143
10.6 IPS
 
Object Detection (I8)
97% 160
11.9 IPS
 
Face Detection (F32)
100% 314
3.73 IPS
 
Face Detection (F16)
100% 309
3.67 IPS
 
Face Detection (I8)
99% 309
3.67 IPS
 
Depth Estimation (F32)
100% 409
3.17 IPS
 
Depth Estimation (F16)
100% 384
2.98 IPS
 
Depth Estimation (I8)
99% 382
2.96 IPS
 
Style Transfer (F32)
100% 1318
1.73 IPS
 
Style Transfer (F16)
100% 1319
1.74 IPS
 
Style Transfer (I8)
100% 1323
1.74 IPS
 
Image Super-Resolution (F32)
100% 369
13.2 IPS
 
Image Super-Resolution (F16)
100% 367
13.1 IPS
 
Image Super-Resolution (I8)
100% 366
13.1 IPS
 
Text Classification (F32)
100% 139
199.1 IPS
 
Text Classification (F16)
100% 114
164.2 IPS
 
Text Classification (I8)
96% 115
165.2 IPS
 
Machine Translation (F32)
100% 221
4.06 IPS
 
Machine Translation (F16)
100% 187
3.44 IPS
 
Machine Translation (I8)
99% 221
4.07 IPS
 

Compare

Set Baseline Geekbench 6 now available