Geekbench ML Score

2382
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date July 26 2024 10:26 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model GEEKOM XT13 Pro
Motherboard Default string XT13 Pro
Power PlanBalanced
CPU Information
Name Intel Core i9-13900H
Topology 1 Processor, 14 Cores, 20 Threads
Identifier GenuineIntel Family 6 Model 186 Stepping 2
Base Frequency 2.60 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% 1226
229.4 IPS
 
Image Classification (F16)
100% 1183
221.4 IPS
 
Image Classification (I8)
100% 954
178.4 IPS
 
Image Segmentation (F32)
100% 1872
31.3 IPS
 
Image Segmentation (F16)
100% 1760
29.4 IPS
 
Image Segmentation (I8)
98% 1304
21.8 IPS
 
Pose Estimation (F32)
100% 9762
11.8 IPS
 
Pose Estimation (F16)
100% 9880
12.0 IPS
 
Pose Estimation (I8)
100% 5481
6.64 IPS
 
Object Detection (F32)
100% 1053
78.6 IPS
 
Object Detection (F16)
100% 1038
77.5 IPS
 
Object Detection (I8)
54% 875
65.3 IPS
 
Face Detection (F32)
100% 2698
32.1 IPS
 
Face Detection (F16)
100% 2666
31.7 IPS
 
Face Detection (I8)
89% 1789
21.3 IPS
 
Depth Estimation (F32)
100% 6032
46.8 IPS
 
Depth Estimation (F16)
100% 6012
46.6 IPS
 
Depth Estimation (I8)
95% 4311
33.4 IPS
 
Style Transfer (F32)
100% 26509
34.9 IPS
 
Style Transfer (F16)
100% 26616
35.0 IPS
 
Style Transfer (I8)
98% 16814
22.1 IPS
 
Image Super-Resolution (F32)
100% 3677
131.3 IPS
 
Image Super-Resolution (F16)
100% 3654
130.5 IPS
 
Image Super-Resolution (I8)
99% 1600
57.1 IPS
 
Text Classification (F32)
100% 866
1.24 KIPS
 
Text Classification (F16)
100% 876
1.26 KIPS
 
Text Classification (I8)
98% 498
716.4 IPS
 
Machine Translation (F32)
100% 815
15.0 IPS
 
Machine Translation (F16)
100% 826
15.2 IPS
 
Machine Translation (I8)
70% 519
9.55 IPS
 

Compare

Set Baseline Geekbench 6 now available