Geekbench ML Score

14189
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date December 18 2024 10:41 AM
Views 4

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model LENOVO 21KWS56V00
Motherboard LENOVO 21KWS56V00
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% 6878
1.29 KIPS
 
Image Classification (F16)
100% 6627
1.24 KIPS
 
Image Classification (I8)
100% 5705
1.07 KIPS
 
Image Segmentation (F32)
100% 8816
147.2 IPS
 
Image Segmentation (F16)
100% 10180
170.0 IPS
 
Image Segmentation (I8)
98% 9588
160.1 IPS
 
Pose Estimation (F32)
100% 98974
119.9 IPS
 
Pose Estimation (F16)
100% 100145
121.3 IPS
 
Pose Estimation (I8)
100% 87092
105.5 IPS
 
Object Detection (F32)
100% 5303
395.9 IPS
 
Object Detection (F16)
100% 5351
399.5 IPS
 
Object Detection (I8)
63% 4788
357.5 IPS
 
Face Detection (F32)
100% 17846
212.2 IPS
 
Face Detection (F16)
100% 19054
226.6 IPS
 
Face Detection (I8)
89% 15840
188.3 IPS
 
Depth Estimation (F32)
100% 40713
315.7 IPS
 
Depth Estimation (F16)
100% 35710
276.9 IPS
 
Depth Estimation (I8)
94% 30586
237.2 IPS
 
Style Transfer (F32)
100% 159303
209.5 IPS
 
Style Transfer (F16)
100% 144323
189.8 IPS
 
Style Transfer (I8)
98% 130840
172.1 IPS
 
Image Super-Resolution (F32)
100% 27050
966.1 IPS
 
Image Super-Resolution (F16)
100% 27120
968.5 IPS
 
Image Super-Resolution (I8)
99% 20033
715.4 IPS
 
Text Classification (F32)
100% 2312
3.32 KIPS
 
Text Classification (F16)
100% 2142
3.08 KIPS
 
Text Classification (I8)
98% 1354
1.95 KIPS
 
Machine Translation (F32)
100% 3238
59.6 IPS
 
Machine Translation (F16)
100% 3228
59.4 IPS
 
Machine Translation (I8)
70% 1861
34.2 IPS
 

Compare

Set Baseline Geekbench 6 now available