Geekbench ML Score

1651
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User dynamiteCobra88
Upload Date November 18 2024 09:32 PM
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% 595
111.4 IPS
 
Image Classification (F16)
100% 641
120.0 IPS
 
Image Classification (I8)
100% 570
106.6 IPS
 
Image Segmentation (F32)
100% 749
12.5 IPS
 
Image Segmentation (F16)
100% 762
12.7 IPS
 
Image Segmentation (I8)
98% 675
11.3 IPS
 
Pose Estimation (F32)
100% 7031
8.51 IPS
 
Pose Estimation (F16)
100% 7050
8.54 IPS
 
Pose Estimation (I8)
100% 6279
7.60 IPS
 
Object Detection (F32)
100% 582
43.4 IPS
 
Object Detection (F16)
100% 578
43.2 IPS
 
Object Detection (I8)
54% 535
39.9 IPS
 
Face Detection (F32)
100% 957
11.4 IPS
 
Face Detection (F16)
100% 1017
12.1 IPS
 
Face Detection (I8)
89% 892
10.6 IPS
 
Depth Estimation (F32)
100% 3523
27.3 IPS
 
Depth Estimation (F16)
100% 3574
27.7 IPS
 
Depth Estimation (I8)
95% 3143
24.4 IPS
 
Style Transfer (F32)
100% 19644
25.8 IPS
 
Style Transfer (F16)
100% 18830
24.8 IPS
 
Style Transfer (I8)
98% 15797
20.8 IPS
 
Image Super-Resolution (F32)
100% 3848
137.4 IPS
 
Image Super-Resolution (F16)
100% 3647
130.2 IPS
 
Image Super-Resolution (I8)
99% 2543
90.8 IPS
 
Text Classification (F32)
90% 395
567.4 IPS
 
Text Classification (F16)
90% 456
655.9 IPS
 
Text Classification (I8)
90% 326
468.3 IPS
 
Machine Translation (F32)
100% 1548
28.5 IPS
 
Machine Translation (F16)
100% 1551
28.5 IPS
 
Machine Translation (I8)
70% 725
13.3 IPS
 

Compare

Set Baseline Geekbench 6 now available