Geekbench ML Score

4171
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date September 25 2024 09:03 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Home Single Language (64-bit)
Model LENOVO 83D4
Motherboard LENOVO LNVNB161216
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 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2404
449.9 IPS
 
Image Classification (F16)
100% 2357
441.2 IPS
 
Image Classification (I8)
100% 1963
367.4 IPS
 
Image Segmentation (F32)
100% 3046
50.9 IPS
 
Image Segmentation (F16)
100% 2964
49.5 IPS
 
Image Segmentation (I8)
98% 2494
41.7 IPS
 
Pose Estimation (F32)
100% 17454
21.1 IPS
 
Pose Estimation (F16)
100% 17415
21.1 IPS
 
Pose Estimation (I8)
100% 13574
16.4 IPS
 
Object Detection (F32)
100% 1647
122.9 IPS
 
Object Detection (F16)
100% 1586
118.4 IPS
 
Object Detection (I8)
54% 1781
133.0 IPS
 
Face Detection (F32)
100% 4677
55.6 IPS
 
Face Detection (F16)
100% 4725
56.2 IPS
 
Face Detection (I8)
89% 3361
40.0 IPS
 
Depth Estimation (F32)
100% 10546
81.8 IPS
 
Depth Estimation (F16)
100% 10431
80.9 IPS
 
Depth Estimation (I8)
95% 8416
65.3 IPS
 
Style Transfer (F32)
100% 47052
61.9 IPS
 
Style Transfer (F16)
100% 46715
61.4 IPS
 
Style Transfer (I8)
98% 34482
45.4 IPS
 
Image Super-Resolution (F32)
100% 7965
284.5 IPS
 
Image Super-Resolution (F16)
100% 8032
286.8 IPS
 
Image Super-Resolution (I8)
99% 4456
159.1 IPS
 
Text Classification (F32)
90% 732
1.05 KIPS
 
Text Classification (F16)
90% 745
1.07 KIPS
 
Text Classification (I8)
90% 557
800.1 IPS
 
Machine Translation (F32)
100% 1417
26.1 IPS
 
Machine Translation (F16)
100% 1433
26.4 IPS
 
Machine Translation (I8)
70% 919
16.9 IPS
 

Compare

Set Baseline Geekbench 6 now available