Geekbench ML Score

270
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date January 07 2024 09:05 PM
Views 1

System Information

System Information
Operating System iOS 16.7.4
Model iPad Pro (9.7-inch)
Model IDiPad6,4
Motherboard J128AP
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 1.92 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 139
26.1 IPS
 
Image Classification (F16)
100% 124
23.1 IPS
 
Image Classification (I8)
99% 123
23.0 IPS
 
Image Segmentation (F32)
100% 117
1.96 IPS
 
Image Segmentation (F16)
100% 118
1.97 IPS
 
Image Segmentation (I8)
100% 118
1.97 IPS
 
Pose Estimation (F32)
100% 821
0.99 IPS
 
Pose Estimation (F16)
100% 812
0.98 IPS
 
Pose Estimation (I8)
100% 817
0.99 IPS
 
Object Detection (F32)
100% 151
11.3 IPS
 
Object Detection (F16)
100% 136
10.1 IPS
 
Object Detection (I8)
97% 152
11.3 IPS
 
Face Detection (F32)
100% 290
3.44 IPS
 
Face Detection (F16)
100% 285
3.39 IPS
 
Face Detection (I8)
99% 287
3.41 IPS
 
Depth Estimation (F32)
100% 403
3.12 IPS
 
Depth Estimation (F16)
100% 371
2.88 IPS
 
Depth Estimation (I8)
99% 369
2.87 IPS
 
Style Transfer (F32)
100% 1296
1.70 IPS
 
Style Transfer (F16)
100% 1295
1.70 IPS
 
Style Transfer (I8)
100% 1296
1.70 IPS
 
Image Super-Resolution (F32)
100% 356
12.7 IPS
 
Image Super-Resolution (F16)
100% 353
12.6 IPS
 
Image Super-Resolution (I8)
100% 353
12.6 IPS
 
Text Classification (F32)
100% 136
195.0 IPS
 
Text Classification (F16)
100% 113
162.7 IPS
 
Text Classification (I8)
96% 114
163.3 IPS
 
Machine Translation (F32)
100% 204
3.75 IPS
 
Machine Translation (F16)
100% 175
3.21 IPS
 
Machine Translation (I8)
99% 206
3.80 IPS
 

Compare

Set Baseline Geekbench 6 now available