Geekbench ML Score

13677
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date August 21 2024 02:08 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% 6391
1.20 KIPS
 
Image Classification (F16)
100% 6957
1.30 KIPS
 
Image Classification (I8)
100% 6100
1.14 KIPS
 
Image Segmentation (F32)
100% 8941
149.3 IPS
 
Image Segmentation (F16)
100% 8983
150.0 IPS
 
Image Segmentation (I8)
98% 8284
138.4 IPS
 
Pose Estimation (F32)
100% 97115
117.6 IPS
 
Pose Estimation (F16)
100% 99333
120.3 IPS
 
Pose Estimation (I8)
100% 86566
104.8 IPS
 
Object Detection (F32)
100% 4788
357.5 IPS
 
Object Detection (F16)
100% 4725
352.7 IPS
 
Object Detection (I8)
63% 4491
335.3 IPS
 
Face Detection (F32)
100% 16761
199.3 IPS
 
Face Detection (F16)
100% 17809
211.7 IPS
 
Face Detection (I8)
89% 14560
173.1 IPS
 
Depth Estimation (F32)
100% 37797
293.1 IPS
 
Depth Estimation (F16)
100% 33728
261.6 IPS
 
Depth Estimation (I8)
94% 32022
248.3 IPS
 
Style Transfer (F32)
100% 145367
191.2 IPS
 
Style Transfer (F16)
100% 145469
191.4 IPS
 
Style Transfer (I8)
98% 132354
174.1 IPS
 
Image Super-Resolution (F32)
100% 29281
1.05 KIPS
 
Image Super-Resolution (F16)
100% 29002
1.04 KIPS
 
Image Super-Resolution (I8)
99% 20657
737.7 IPS
 
Text Classification (F32)
100% 1916
2.75 KIPS
 
Text Classification (F16)
100% 1937
2.78 KIPS
 
Text Classification (I8)
98% 1303
1.87 KIPS
 
Machine Translation (F32)
100% 3165
58.2 IPS
 
Machine Translation (F16)
100% 3186
58.6 IPS
 
Machine Translation (I8)
70% 1850
34.0 IPS
 

Compare

Set Baseline Geekbench 6 now available