Geekbench ML Score

3089
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date May 09 2024 02:43 AM
Views 3

System Information

System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model LENOVO 83DN
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% 1389
259.9 IPS
 
Image Classification (F16)
100% 1432
268.0 IPS
 
Image Classification (I8)
100% 1255
234.8 IPS
 
Image Segmentation (F32)
100% 1534
25.6 IPS
 
Image Segmentation (F16)
100% 1601
26.7 IPS
 
Image Segmentation (I8)
98% 1414
23.6 IPS
 
Pose Estimation (F32)
100% 14196
17.2 IPS
 
Pose Estimation (F16)
100% 14778
17.9 IPS
 
Pose Estimation (I8)
100% 12472
15.1 IPS
 
Object Detection (F32)
100% 1292
96.5 IPS
 
Object Detection (F16)
100% 1334
99.6 IPS
 
Object Detection (I8)
54% 1158
86.4 IPS
 
Face Detection (F32)
100% 1379
16.4 IPS
 
Face Detection (F16)
100% 1375
16.3 IPS
 
Face Detection (I8)
89% 1224
14.6 IPS
 
Depth Estimation (F32)
100% 7939
61.6 IPS
 
Depth Estimation (F16)
100% 8033
62.3 IPS
 
Depth Estimation (I8)
95% 6682
51.8 IPS
 
Style Transfer (F32)
100% 41065
54.0 IPS
 
Style Transfer (F16)
100% 40921
53.8 IPS
 
Style Transfer (I8)
98% 32438
42.7 IPS
 
Image Super-Resolution (F32)
100% 7636
272.7 IPS
 
Image Super-Resolution (F16)
100% 6927
247.4 IPS
 
Image Super-Resolution (I8)
99% 5211
186.1 IPS
 
Text Classification (F32)
90% 775
1.11 KIPS
 
Text Classification (F16)
90% 753
1.08 KIPS
 
Text Classification (I8)
90% 571
820.8 IPS
 
Machine Translation (F32)
100% 1567
28.8 IPS
 
Machine Translation (F16)
100% 1582
29.1 IPS
 
Machine Translation (I8)
70% 892
16.4 IPS
 

Compare

Set Baseline Geekbench 6 now available