Geekbench ML Score

3726
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date March 27 2025 05:02 AM
Views 3

System Information

System Information
Operating System Microsoft Windows 11 (64-bit)
Model LENOVO 21QESIT004
Motherboard LENOVO 21QESIT004
CPU Information
Name Intel(R) Core(TM) Ultra 7 265H
Topology 1 Processor, 16 Cores
Identifier GenuineIntel Family 6 Model 197 Stepping 2
Base Frequency 2.20 GHz
Cluster 16 Cores
Cluster 210 Cores
L1 Instruction Cache64.0 KB x 8
L1 Data Cache48.0 KB x 8
L2 Cache3.00 MB x 2
L3 Cache24.0 MB x 1
Memory Information
Size 8.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2737
512.2 IPS
 
Image Classification (F16)
100% 2673
500.2 IPS
 
Image Classification (I8)
99% 2238
418.9 IPS
 
Image Segmentation (F32)
100% 2090
34.9 IPS
 
Image Segmentation (F16)
100% 2081
34.8 IPS
 
Image Segmentation (I8)
98% 1542
25.8 IPS
 
Pose Estimation (F32)
100% 12394
15.0 IPS
 
Pose Estimation (F16)
100% 13500
16.3 IPS
 
Pose Estimation (I8)
100% 10357
12.5 IPS
 
Object Detection (F32)
100% 2484
185.5 IPS
 
Object Detection (F16)
100% 2516
187.8 IPS
 
Object Detection (I8)
60% 2125
158.6 IPS
 
Face Detection (F32)
100% 2730
32.5 IPS
 
Face Detection (F16)
100% 2704
32.1 IPS
 
Face Detection (I8)
88% 1856
22.1 IPS
 
Depth Estimation (F32)
100% 10242
79.4 IPS
 
Depth Estimation (F16)
100% 10528
81.6 IPS
 
Depth Estimation (I8)
95% 7343
56.9 IPS
 
Style Transfer (F32)
100% 39507
52.0 IPS
 
Style Transfer (F16)
100% 37968
49.9 IPS
 
Style Transfer (I8)
98% 24207
31.8 IPS
 
Image Super-Resolution (F32)
100% 6330
226.1 IPS
 
Image Super-Resolution (F16)
100% 6347
226.7 IPS
 
Image Super-Resolution (I8)
99% 3762
134.4 IPS
 
Text Classification (F32)
90% 825
1.19 KIPS
 
Text Classification (F16)
90% 843
1.21 KIPS
 
Text Classification (I8)
90% 628
903.3 IPS
 
Machine Translation (F32)
100% 1499
27.6 IPS
 
Machine Translation (F16)
100% 1488
27.4 IPS
 
Machine Translation (I8)
70% 940
17.3 IPS
 

Compare

Set Baseline Geekbench 6 now available