Geekbench ML Score

1663
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User dynamiteCobra88
Upload Date November 18 2024 09:19 PM
Views 3

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% 596
111.6 IPS
 
Image Classification (F16)
100% 603
112.9 IPS
 
Image Classification (I8)
100% 560
104.8 IPS
 
Image Segmentation (F32)
100% 781
13.0 IPS
 
Image Segmentation (F16)
100% 773
12.9 IPS
 
Image Segmentation (I8)
98% 688
11.5 IPS
 
Pose Estimation (F32)
100% 7122
8.62 IPS
 
Pose Estimation (F16)
100% 7123
8.63 IPS
 
Pose Estimation (I8)
100% 6377
7.72 IPS
 
Object Detection (F32)
100% 622
46.4 IPS
 
Object Detection (F16)
100% 575
42.9 IPS
 
Object Detection (I8)
54% 555
41.4 IPS
 
Face Detection (F32)
100% 1012
12.0 IPS
 
Face Detection (F16)
100% 1014
12.1 IPS
 
Face Detection (I8)
89% 890
10.6 IPS
 
Depth Estimation (F32)
100% 3545
27.5 IPS
 
Depth Estimation (F16)
100% 3215
24.9 IPS
 
Depth Estimation (I8)
95% 3143
24.4 IPS
 
Style Transfer (F32)
100% 19314
25.4 IPS
 
Style Transfer (F16)
100% 18767
24.7 IPS
 
Style Transfer (I8)
98% 16085
21.2 IPS
 
Image Super-Resolution (F32)
100% 3506
125.2 IPS
 
Image Super-Resolution (F16)
100% 3542
126.5 IPS
 
Image Super-Resolution (I8)
99% 2557
91.3 IPS
 
Text Classification (F32)
90% 515
739.9 IPS
 
Text Classification (F16)
90% 384
551.8 IPS
 
Text Classification (I8)
90% 386
554.3 IPS
 
Machine Translation (F32)
100% 1544
28.4 IPS
 
Machine Translation (F16)
100% 1519
27.9 IPS
 
Machine Translation (I8)
70% 730
13.4 IPS
 

Compare

Set Baseline Geekbench 6 now available