Geekbench ML Score

1737
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User dynamiteCobra88
Upload Date November 18 2024 07:43 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model Microsoft Corporation Surface Pro 10 for Business
Motherboard Microsoft Corporation Surface Pro 10 for Business
Power PlanBalanced
CPU Information
Name Intel(R) Core(TM) Ultra 5 135U
Topology 1 Processor, 12 Cores, 14 Threads
Identifier GenuineIntel Family 6 Model 170 Stepping 4
Base Frequency 2.10 GHz
Cluster 12 Cores
Cluster 210 Cores
L1 Instruction Cache64.0 KB x 7
L1 Data Cache48.0 KB x 7
L2 Cache2.00 MB x 1
L3 Cache12.0 MB x 1
Memory Information
Size 16.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 613
114.7 IPS
 
Image Classification (F16)
100% 606
113.3 IPS
 
Image Classification (I8)
100% 564
105.5 IPS
 
Image Segmentation (F32)
100% 784
13.1 IPS
 
Image Segmentation (F16)
100% 783
13.1 IPS
 
Image Segmentation (I8)
98% 698
11.7 IPS
 
Pose Estimation (F32)
100% 7024
8.51 IPS
 
Pose Estimation (F16)
100% 7014
8.49 IPS
 
Pose Estimation (I8)
100% 6252
7.57 IPS
 
Object Detection (F32)
100% 603
45.0 IPS
 
Object Detection (F16)
100% 599
44.7 IPS
 
Object Detection (I8)
54% 560
41.8 IPS
 
Face Detection (F32)
100% 1021
12.1 IPS
 
Face Detection (F16)
100% 1010
12.0 IPS
 
Face Detection (I8)
89% 906
10.8 IPS
 
Depth Estimation (F32)
100% 3544
27.5 IPS
 
Depth Estimation (F16)
100% 3561
27.6 IPS
 
Depth Estimation (I8)
95% 3087
23.9 IPS
 
Style Transfer (F32)
100% 19355
25.5 IPS
 
Style Transfer (F16)
100% 19486
25.6 IPS
 
Style Transfer (I8)
98% 15632
20.6 IPS
 
Image Super-Resolution (F32)
100% 3526
125.9 IPS
 
Image Super-Resolution (F16)
100% 3518
125.6 IPS
 
Image Super-Resolution (I8)
99% 2635
94.1 IPS
 
Text Classification (F32)
90% 628
902.6 IPS
 
Text Classification (F16)
90% 631
906.8 IPS
 
Text Classification (I8)
90% 444
638.1 IPS
 
Machine Translation (F32)
100% 1719
31.6 IPS
 
Machine Translation (F16)
100% 1747
32.1 IPS
 
Machine Translation (I8)
70% 757
13.9 IPS
 

Compare

Set Baseline Geekbench 6 now available