Geekbench ML Score

12645
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date August 21 2024 02:01 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% 6268
1.17 KIPS
 
Image Classification (F16)
100% 6826
1.28 KIPS
 
Image Classification (I8)
100% 6069
1.14 KIPS
 
Image Segmentation (F32)
100% 7464
124.7 IPS
 
Image Segmentation (F16)
100% 8625
144.1 IPS
 
Image Segmentation (I8)
98% 8363
139.7 IPS
 
Pose Estimation (F32)
100% 98640
119.4 IPS
 
Pose Estimation (F16)
100% 97497
118.1 IPS
 
Pose Estimation (I8)
100% 85630
103.7 IPS
 
Object Detection (F32)
100% 4623
345.1 IPS
 
Object Detection (F16)
100% 2678
199.9 IPS
 
Object Detection (I8)
63% 4245
316.9 IPS
 
Face Detection (F32)
100% 15222
181.0 IPS
 
Face Detection (F16)
100% 14585
173.4 IPS
 
Face Detection (I8)
89% 12034
143.1 IPS
 
Depth Estimation (F32)
100% 35440
274.8 IPS
 
Depth Estimation (F16)
100% 34838
270.2 IPS
 
Depth Estimation (I8)
94% 27385
212.4 IPS
 
Style Transfer (F32)
100% 144527
190.1 IPS
 
Style Transfer (F16)
100% 138333
182.0 IPS
 
Style Transfer (I8)
98% 128909
169.6 IPS
 
Image Super-Resolution (F32)
100% 26468
945.3 IPS
 
Image Super-Resolution (F16)
100% 25699
917.8 IPS
 
Image Super-Resolution (I8)
99% 21353
762.6 IPS
 
Text Classification (F32)
100% 1854
2.67 KIPS
 
Text Classification (F16)
100% 1892
2.72 KIPS
 
Text Classification (I8)
98% 1307
1.88 KIPS
 
Machine Translation (F32)
100% 3154
58.0 IPS
 
Machine Translation (F16)
100% 2577
47.4 IPS
 
Machine Translation (I8)
70% 1501
27.6 IPS
 

Compare

Set Baseline Geekbench 6 now available