Geekbench ML Score

1738
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User dynamiteCobra88
Upload Date November 18 2024 07:51 AM
Views 1

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% 644
120.6 IPS
 
Image Classification (F16)
100% 616
115.3 IPS
 
Image Classification (I8)
100% 548
102.6 IPS
 
Image Segmentation (F32)
100% 787
13.1 IPS
 
Image Segmentation (F16)
100% 784
13.1 IPS
 
Image Segmentation (I8)
98% 701
11.7 IPS
 
Pose Estimation (F32)
100% 6882
8.33 IPS
 
Pose Estimation (F16)
100% 7009
8.49 IPS
 
Pose Estimation (I8)
100% 6205
7.51 IPS
 
Object Detection (F32)
100% 611
45.6 IPS
 
Object Detection (F16)
100% 611
45.6 IPS
 
Object Detection (I8)
54% 569
42.5 IPS
 
Face Detection (F32)
100% 962
11.4 IPS
 
Face Detection (F16)
100% 1021
12.1 IPS
 
Face Detection (I8)
89% 896
10.7 IPS
 
Depth Estimation (F32)
100% 3664
28.4 IPS
 
Depth Estimation (F16)
100% 3600
27.9 IPS
 
Depth Estimation (I8)
95% 3120
24.2 IPS
 
Style Transfer (F32)
100% 19424
25.6 IPS
 
Style Transfer (F16)
100% 19132
25.2 IPS
 
Style Transfer (I8)
98% 15586
20.5 IPS
 
Image Super-Resolution (F32)
100% 3539
126.4 IPS
 
Image Super-Resolution (F16)
100% 3618
129.2 IPS
 
Image Super-Resolution (I8)
99% 2608
93.1 IPS
 
Text Classification (F32)
90% 630
905.9 IPS
 
Text Classification (F16)
90% 618
887.6 IPS
 
Text Classification (I8)
90% 438
629.8 IPS
 
Machine Translation (F32)
100% 1708
31.4 IPS
 
Machine Translation (F16)
100% 1716
31.6 IPS
 
Machine Translation (I8)
70% 765
14.1 IPS
 

Compare

Set Baseline Geekbench 6 now available