Geekbench ML Score

605
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date February 11 2025 10:23 AM
Views 6

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% 228
42.7 IPS
 
Image Classification (F16)
100% 221
41.3 IPS
 
Image Classification (I8)
99% 285
53.4 IPS
 
Image Segmentation (F32)
100% 189
3.16 IPS
 
Image Segmentation (F16)
100% 183
3.05 IPS
 
Image Segmentation (I8)
100% 182
3.05 IPS
 
Pose Estimation (F32)
100% 1991
2.41 IPS
 
Pose Estimation (F16)
100% 1963
2.38 IPS
 
Pose Estimation (I8)
100% 1960
2.37 IPS
 
Object Detection (F32)
100% 343
25.6 IPS
 
Object Detection (F16)
100% 341
25.5 IPS
 
Object Detection (I8)
97% 348
26.0 IPS
 
Face Detection (F32)
100% 1362
16.2 IPS
 
Face Detection (F16)
100% 1314
15.6 IPS
 
Face Detection (I8)
99% 1330
15.8 IPS
 
Depth Estimation (F32)
100% 2120
16.4 IPS
 
Depth Estimation (F16)
100% 2077
16.1 IPS
 
Depth Estimation (I8)
99% 2162
16.8 IPS
 
Style Transfer (F32)
100% 4713
6.20 IPS
 
Style Transfer (F16)
100% 4724
6.21 IPS
 
Style Transfer (I8)
100% 4705
6.19 IPS
 
Image Super-Resolution (F32)
100% 1156
41.3 IPS
 
Image Super-Resolution (F16)
100% 1003
35.8 IPS
 
Image Super-Resolution (I8)
100% 1097
39.2 IPS
 
Text Classification (F32)
100% 43
61.7 IPS
 
Text Classification (F16)
100% 101
144.9 IPS
 
Text Classification (I8)
96% 100
144.2 IPS
 
Machine Translation (F32)
100% 208
3.83 IPS
 
Machine Translation (F16)
100% 177
3.25 IPS
 
Machine Translation (I8)
99% 212
3.91 IPS
 

Compare

Set Baseline Geekbench 6 now available