Geekbench ML Score

2679
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date May 31 2025 11:14 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model Alder lake Intel RVP
Motherboard Alder lake Intel RVP
Power PlanHigh performance
CPU Information
Name Intel Core i9-12900H
Topology 1 Processor, 14 Cores, 20 Threads
Identifier GenuineIntel Family 6 Model 154 Stepping 3
Base Frequency 2.50 GHz
Cluster 16 Cores
Cluster 28 Cores
L1 Instruction Cache32.0 KB x 10
L1 Data Cache48.0 KB x 10
L2 Cache1.25 MB x 2
L3 Cache24.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Iris(R) Xe Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1273
238.3 IPS
 
Image Classification (F16)
100% 1239
231.8 IPS
 
Image Classification (I8)
100% 988
184.9 IPS
 
Image Segmentation (F32)
100% 2113
35.3 IPS
 
Image Segmentation (F16)
100% 2101
35.1 IPS
 
Image Segmentation (I8)
98% 1503
25.1 IPS
 
Pose Estimation (F32)
100% 12722
15.4 IPS
 
Pose Estimation (F16)
100% 12803
15.5 IPS
 
Pose Estimation (I8)
100% 6150
7.45 IPS
 
Object Detection (F32)
100% 1447
108.0 IPS
 
Object Detection (F16)
100% 1458
108.8 IPS
 
Object Detection (I8)
54% 1181
88.2 IPS
 
Face Detection (F32)
100% 2976
35.4 IPS
 
Face Detection (F16)
100% 3003
35.7 IPS
 
Face Detection (I8)
89% 1971
23.4 IPS
 
Depth Estimation (F32)
100% 6319
49.0 IPS
 
Depth Estimation (F16)
100% 6258
48.5 IPS
 
Depth Estimation (I8)
95% 4415
34.2 IPS
 
Style Transfer (F32)
100% 26616
35.0 IPS
 
Style Transfer (F16)
100% 27107
35.7 IPS
 
Style Transfer (I8)
98% 16863
22.2 IPS
 
Image Super-Resolution (F32)
100% 3900
139.3 IPS
 
Image Super-Resolution (F16)
100% 3887
138.8 IPS
 
Image Super-Resolution (I8)
99% 1639
58.5 IPS
 
Text Classification (F32)
100% 808
1.16 KIPS
 
Text Classification (F16)
100% 778
1.12 KIPS
 
Text Classification (I8)
98% 422
606.0 IPS
 
Machine Translation (F32)
100% 1322
24.3 IPS
 
Machine Translation (F16)
100% 1326
24.4 IPS
 
Machine Translation (I8)
70% 622
11.4 IPS
 

Compare

Set Baseline Geekbench 6 now available