Geekbench ML Score

2931
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User Clementin
Upload Date June 04 2025 05:31 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Famille (64-bit)
Model GIGABYTE A5 X1
Motherboard GIGABYTE A5 X1
Power PlanUtilisation normale
CPU Information
Name AMD Ryzen 9 5900HX
Topology 1 Processor, 8 Cores, 16 Threads
Identifier AuthenticAMD Family 25 Model 80 Stepping 0
Base Frequency 3.30 GHz
Cluster 18 Cores
L1 Instruction Cache32.0 KB x 8
L1 Data Cache32.0 KB x 8
L2 Cache512 KB x 8
L3 Cache16.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device AMD Radeon(TM) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1250
233.8 IPS
 
Image Classification (F16)
100% 1232
230.4 IPS
 
Image Classification (I8)
99% 1046
195.7 IPS
 
Image Segmentation (F32)
100% 1481
24.7 IPS
 
Image Segmentation (F16)
100% 1462
24.4 IPS
 
Image Segmentation (I8)
98% 1255
21.0 IPS
 
Pose Estimation (F32)
100% 13150
15.9 IPS
 
Pose Estimation (F16)
100% 13126
15.9 IPS
 
Pose Estimation (I8)
100% 10653
12.9 IPS
 
Object Detection (F32)
100% 1240
92.6 IPS
 
Object Detection (F16)
100% 1244
92.9 IPS
 
Object Detection (I8)
67% 1113
83.1 IPS
 
Face Detection (F32)
100% 2903
34.5 IPS
 
Face Detection (F16)
100% 2890
34.4 IPS
 
Face Detection (I8)
89% 2224
26.4 IPS
 
Depth Estimation (F32)
100% 7407
57.4 IPS
 
Depth Estimation (F16)
100% 7424
57.6 IPS
 
Depth Estimation (I8)
94% 5800
45.0 IPS
 
Style Transfer (F32)
100% 22753
29.9 IPS
 
Style Transfer (F16)
100% 22755
29.9 IPS
 
Style Transfer (I8)
98% 17705
23.3 IPS
 
Image Super-Resolution (F32)
100% 4684
167.3 IPS
 
Image Super-Resolution (F16)
100% 4881
174.3 IPS
 
Image Super-Resolution (I8)
99% 3270
116.8 IPS
 
Text Classification (F32)
100% 1019
1.46 KIPS
 
Text Classification (F16)
100% 1026
1.47 KIPS
 
Text Classification (I8)
98% 669
961.9 IPS
 
Machine Translation (F32)
100% 1731
31.8 IPS
 
Machine Translation (F16)
100% 1748
32.2 IPS
 
Machine Translation (I8)
69% 867
16.0 IPS
 

Compare

Set Baseline Geekbench 6 now available