Geekbench ML Score

5230
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date January 08 2025 05:30 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model LENOVO 83HM
Motherboard LENOVO LNVNB161216
Power PlanBalanced
CPU Information
Name Intel(R) Core(TM) Ultra 7 258V
Topology 1 Processor, 8 Cores
Identifier GenuineIntel Family 6 Model 189 Stepping 1
Base Frequency 2.20 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache64.0 KB x 4
L1 Data Cache48.0 KB x 4
L2 Cache2.50 MB x 1
L3 Cache12.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) 140V GPU (16GB)

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3279
613.7 IPS
 
Image Classification (F16)
100% 2426
453.9 IPS
 
Image Classification (I8)
100% 2585
483.8 IPS
 
Image Segmentation (F32)
100% 5837
97.5 IPS
 
Image Segmentation (F16)
100% 6032
100.7 IPS
 
Image Segmentation (I8)
98% 4505
75.2 IPS
 
Pose Estimation (F32)
100% 20671
25.0 IPS
 
Pose Estimation (F16)
100% 19577
23.7 IPS
 
Pose Estimation (I8)
100% 15512
18.8 IPS
 
Object Detection (F32)
100% 2795
208.7 IPS
 
Object Detection (F16)
100% 2780
207.6 IPS
 
Object Detection (I8)
61% 2286
170.6 IPS
 
Face Detection (F32)
100% 7738
92.0 IPS
 
Face Detection (F16)
100% 7637
90.8 IPS
 
Face Detection (I8)
89% 4924
58.5 IPS
 
Depth Estimation (F32)
100% 17665
137.0 IPS
 
Depth Estimation (F16)
100% 17504
135.7 IPS
 
Depth Estimation (I8)
94% 14319
111.0 IPS
 
Style Transfer (F32)
100% 47872
63.0 IPS
 
Style Transfer (F16)
100% 48453
63.7 IPS
 
Style Transfer (I8)
98% 38547
50.7 IPS
 
Image Super-Resolution (F32)
100% 6990
249.6 IPS
 
Image Super-Resolution (F16)
100% 7742
276.5 IPS
 
Image Super-Resolution (I8)
99% 4589
163.9 IPS
 
Text Classification (F32)
100% 590
847.9 IPS
 
Text Classification (F16)
100% 556
798.9 IPS
 
Text Classification (I8)
98% 531
762.5 IPS
 
Machine Translation (F32)
100% 1450
26.7 IPS
 
Machine Translation (F16)
100% 1711
31.5 IPS
 
Machine Translation (I8)
70% 799
14.7 IPS
 

Compare

Set Baseline Geekbench 6 now available