Geekbench ML Score

3490
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date March 27 2025 04:59 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% 2344
438.6 IPS
 
Image Classification (F16)
100% 2689
503.2 IPS
 
Image Classification (I8)
99% 2094
391.8 IPS
 
Image Segmentation (F32)
100% 2079
34.7 IPS
 
Image Segmentation (F16)
100% 2103
35.1 IPS
 
Image Segmentation (I8)
98% 1527
25.5 IPS
 
Pose Estimation (F32)
100% 12442
15.1 IPS
 
Pose Estimation (F16)
100% 12773
15.5 IPS
 
Pose Estimation (I8)
100% 9885
12.0 IPS
 
Object Detection (F32)
100% 1703
127.1 IPS
 
Object Detection (F16)
100% 2177
162.6 IPS
 
Object Detection (I8)
60% 1396
104.3 IPS
 
Face Detection (F32)
100% 2668
31.7 IPS
 
Face Detection (F16)
100% 2684
31.9 IPS
 
Face Detection (I8)
88% 1838
21.9 IPS
 
Depth Estimation (F32)
100% 9537
74.0 IPS
 
Depth Estimation (F16)
100% 10190
79.0 IPS
 
Depth Estimation (I8)
95% 7506
58.2 IPS
 
Style Transfer (F32)
100% 34865
45.9 IPS
 
Style Transfer (F16)
100% 38758
51.0 IPS
 
Style Transfer (I8)
98% 24827
32.7 IPS
 
Image Super-Resolution (F32)
100% 5480
195.7 IPS
 
Image Super-Resolution (F16)
100% 6539
233.5 IPS
 
Image Super-Resolution (I8)
99% 3733
133.3 IPS
 
Text Classification (F32)
90% 639
917.7 IPS
 
Text Classification (F16)
90% 837
1.20 KIPS
 
Text Classification (I8)
90% 606
870.7 IPS
 
Machine Translation (F32)
100% 1433
26.4 IPS
 
Machine Translation (F16)
100% 1457
26.8 IPS
 
Machine Translation (I8)
70% 926
17.0 IPS
 

Compare

Set Baseline Geekbench 6 now available