Geekbench ML Score

13748
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date December 18 2024 11:16 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% 6414
1.20 KIPS
 
Image Classification (F16)
100% 6463
1.21 KIPS
 
Image Classification (I8)
100% 5791
1.08 KIPS
 
Image Segmentation (F32)
100% 10002
167.1 IPS
 
Image Segmentation (F16)
100% 10119
169.0 IPS
 
Image Segmentation (I8)
98% 8881
148.3 IPS
 
Pose Estimation (F32)
100% 97171
117.7 IPS
 
Pose Estimation (F16)
100% 97659
118.3 IPS
 
Pose Estimation (I8)
100% 84741
102.6 IPS
 
Object Detection (F32)
100% 5150
384.5 IPS
 
Object Detection (F16)
100% 5211
389.0 IPS
 
Object Detection (I8)
63% 4799
358.2 IPS
 
Face Detection (F32)
100% 17362
206.4 IPS
 
Face Detection (F16)
100% 17803
211.7 IPS
 
Face Detection (I8)
89% 15369
182.7 IPS
 
Depth Estimation (F32)
100% 35573
275.9 IPS
 
Depth Estimation (F16)
100% 36898
286.1 IPS
 
Depth Estimation (I8)
94% 29836
231.4 IPS
 
Style Transfer (F32)
100% 156618
206.0 IPS
 
Style Transfer (F16)
100% 143493
188.8 IPS
 
Style Transfer (I8)
98% 128435
168.9 IPS
 
Image Super-Resolution (F32)
100% 26588
949.5 IPS
 
Image Super-Resolution (F16)
100% 24901
889.3 IPS
 
Image Super-Resolution (I8)
99% 18272
652.5 IPS
 
Text Classification (F32)
100% 2082
2.99 KIPS
 
Text Classification (F16)
100% 1935
2.78 KIPS
 
Text Classification (I8)
98% 1296
1.86 KIPS
 
Machine Translation (F32)
100% 3179
58.5 IPS
 
Machine Translation (F16)
100% 3172
58.4 IPS
 
Machine Translation (I8)
70% 1839
33.9 IPS
 

Compare

Set Baseline Geekbench 6 now available