Geekbench ML Score

13680
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date August 21 2024 06:23 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model LENOVO 21KWZC48US
Motherboard LENOVO 21KWZC48US
Power PlanBalanced
CPU Information
Name Intel Core Ultra 9 185H
Topology 1 Processor, 16 Cores, 22 Threads
Identifier GenuineIntel Family 6 Model 170 Stepping 4
Base Frequency 2.30 GHz
Cluster 16 Cores
Cluster 210 Cores
L1 Instruction Cache64.0 KB x 11
L1 Data Cache48.0 KB x 11
L2 Cache2.00 MB x 2
L3 Cache24.0 MB x 1
Memory Information
Size 64.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device NVIDIA RTX 3000 Ada Generation Laptop GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6610
1.24 KIPS
 
Image Classification (F16)
100% 6664
1.25 KIPS
 
Image Classification (I8)
100% 6096
1.14 KIPS
 
Image Segmentation (F32)
100% 8909
148.8 IPS
 
Image Segmentation (F16)
100% 9021
150.7 IPS
 
Image Segmentation (I8)
98% 8386
140.1 IPS
 
Pose Estimation (F32)
100% 98989
119.9 IPS
 
Pose Estimation (F16)
100% 99194
120.1 IPS
 
Pose Estimation (I8)
100% 86668
105.0 IPS
 
Object Detection (F32)
100% 4975
371.4 IPS
 
Object Detection (F16)
100% 4950
369.5 IPS
 
Object Detection (I8)
63% 4452
332.3 IPS
 
Face Detection (F32)
100% 16944
201.5 IPS
 
Face Detection (F16)
100% 17409
207.0 IPS
 
Face Detection (I8)
89% 15374
182.8 IPS
 
Depth Estimation (F32)
100% 37652
292.0 IPS
 
Depth Estimation (F16)
100% 36952
286.6 IPS
 
Depth Estimation (I8)
94% 28205
218.7 IPS
 
Style Transfer (F32)
100% 146105
192.2 IPS
 
Style Transfer (F16)
100% 142899
188.0 IPS
 
Style Transfer (I8)
98% 133276
175.3 IPS
 
Image Super-Resolution (F32)
100% 28186
1.01 KIPS
 
Image Super-Resolution (F16)
100% 27309
975.3 IPS
 
Image Super-Resolution (I8)
99% 21273
759.7 IPS
 
Text Classification (F32)
100% 1953
2.81 KIPS
 
Text Classification (F16)
100% 1910
2.74 KIPS
 
Text Classification (I8)
98% 1314
1.89 KIPS
 
Machine Translation (F32)
100% 3152
58.0 IPS
 
Machine Translation (F16)
100% 3102
57.1 IPS
 
Machine Translation (I8)
70% 1847
34.0 IPS
 

Compare

Set Baseline Geekbench 6 now available