Geekbench ML Score

1679
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User dynamiteCobra88
Upload Date November 20 2024 12:38 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% 625
117.0 IPS
 
Image Classification (F16)
100% 604
113.1 IPS
 
Image Classification (I8)
100% 544
101.8 IPS
 
Image Segmentation (F32)
100% 772
12.9 IPS
 
Image Segmentation (F16)
100% 775
12.9 IPS
 
Image Segmentation (I8)
98% 692
11.6 IPS
 
Pose Estimation (F32)
100% 7103
8.60 IPS
 
Pose Estimation (F16)
100% 7142
8.65 IPS
 
Pose Estimation (I8)
100% 6342
7.68 IPS
 
Object Detection (F32)
100% 611
45.6 IPS
 
Object Detection (F16)
100% 629
47.0 IPS
 
Object Detection (I8)
54% 564
42.1 IPS
 
Face Detection (F32)
100% 1017
12.1 IPS
 
Face Detection (F16)
100% 1018
12.1 IPS
 
Face Detection (I8)
89% 905
10.8 IPS
 
Depth Estimation (F32)
100% 3602
27.9 IPS
 
Depth Estimation (F16)
100% 3531
27.4 IPS
 
Depth Estimation (I8)
95% 3041
23.6 IPS
 
Style Transfer (F32)
100% 18752
24.7 IPS
 
Style Transfer (F16)
100% 19380
25.5 IPS
 
Style Transfer (I8)
98% 15641
20.6 IPS
 
Image Super-Resolution (F32)
100% 3434
122.7 IPS
 
Image Super-Resolution (F16)
100% 3446
123.1 IPS
 
Image Super-Resolution (I8)
99% 2586
92.3 IPS
 
Text Classification (F32)
90% 514
738.5 IPS
 
Text Classification (F16)
90% 456
655.5 IPS
 
Text Classification (I8)
90% 377
542.1 IPS
 
Machine Translation (F32)
100% 1548
28.5 IPS
 
Machine Translation (F16)
100% 1524
28.0 IPS
 
Machine Translation (I8)
70% 729
13.4 IPS
 

Compare

Set Baseline Geekbench 6 now available