Geekbench ML Score

14383
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date December 18 2024 10:52 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% 6968
1.30 KIPS
 
Image Classification (F16)
100% 6935
1.30 KIPS
 
Image Classification (I8)
100% 6224
1.16 KIPS
 
Image Segmentation (F32)
100% 11258
188.0 IPS
 
Image Segmentation (F16)
100% 10258
171.3 IPS
 
Image Segmentation (I8)
98% 9350
156.1 IPS
 
Pose Estimation (F32)
100% 97973
118.6 IPS
 
Pose Estimation (F16)
100% 99050
119.9 IPS
 
Pose Estimation (I8)
100% 85958
104.1 IPS
 
Object Detection (F32)
100% 5128
382.8 IPS
 
Object Detection (F16)
100% 5219
389.7 IPS
 
Object Detection (I8)
63% 4901
365.9 IPS
 
Face Detection (F32)
100% 17978
213.8 IPS
 
Face Detection (F16)
100% 19164
227.9 IPS
 
Face Detection (I8)
89% 15998
190.2 IPS
 
Depth Estimation (F32)
100% 40702
315.6 IPS
 
Depth Estimation (F16)
100% 36156
280.4 IPS
 
Depth Estimation (I8)
94% 30262
234.7 IPS
 
Style Transfer (F32)
100% 141687
186.4 IPS
 
Style Transfer (F16)
100% 143676
189.0 IPS
 
Style Transfer (I8)
98% 130893
172.2 IPS
 
Image Super-Resolution (F32)
100% 27783
992.2 IPS
 
Image Super-Resolution (F16)
100% 28701
1.02 KIPS
 
Image Super-Resolution (I8)
99% 20419
729.2 IPS
 
Text Classification (F32)
100% 2318
3.33 KIPS
 
Text Classification (F16)
100% 2317
3.33 KIPS
 
Text Classification (I8)
98% 1392
2.00 KIPS
 
Machine Translation (F32)
100% 3204
59.0 IPS
 
Machine Translation (F16)
100% 3208
59.0 IPS
 
Machine Translation (I8)
70% 1873
34.5 IPS
 

Compare

Set Baseline Geekbench 6 now available