Geekbench ML Score

1656
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date April 21 2025 10:42 PM
Views 7

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model Micro-Star International Co., Ltd. MS-7E12
Motherboard Micro-Star International Co., Ltd. MAG X670E TOMAHAWK WIFI (MS-7E12)
Power PlanBalanced
CPU Information
Name AMD Ryzen 9 9950X 16-Core Processor
Topology 1 Processor, 16 Cores, 32 Threads
Identifier AuthenticAMD Family 26 Model 68 Stepping 0
Base Frequency 4.30 GHz
Cluster 116 Cores
L1 Instruction Cache32.0 KB x 16
L1 Data Cache48.0 KB x 16
L2 Cache1.00 MB x 16
L3 Cache32.0 MB x 2
Memory Information
Size 128.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device AMD Radeon(TM) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 584
109.3 IPS
 
Image Classification (F16)
100% 589
110.1 IPS
 
Image Classification (I8)
100% 547
102.3 IPS
 
Image Segmentation (F32)
100% 1055
17.6 IPS
 
Image Segmentation (F16)
100% 1051
17.6 IPS
 
Image Segmentation (I8)
98% 924
15.4 IPS
 
Pose Estimation (F32)
100% 6061
7.34 IPS
 
Pose Estimation (F16)
100% 6039
7.31 IPS
 
Pose Estimation (I8)
100% 5447
6.60 IPS
 
Object Detection (F32)
100% 626
46.7 IPS
 
Object Detection (F16)
100% 642
47.9 IPS
 
Object Detection (I8)
62% 604
45.1 IPS
 
Face Detection (F32)
100% 1690
20.1 IPS
 
Face Detection (F16)
100% 1685
20.0 IPS
 
Face Detection (I8)
89% 1467
17.4 IPS
 
Depth Estimation (F32)
100% 3343
25.9 IPS
 
Depth Estimation (F16)
100% 3343
25.9 IPS
 
Depth Estimation (I8)
94% 3052
23.7 IPS
 
Style Transfer (F32)
100% 10625
14.0 IPS
 
Style Transfer (F16)
100% 10615
14.0 IPS
 
Style Transfer (I8)
98% 9426
12.4 IPS
 
Image Super-Resolution (F32)
100% 2714
96.9 IPS
 
Image Super-Resolution (F16)
100% 2707
96.7 IPS
 
Image Super-Resolution (I8)
99% 2074
74.1 IPS
 
Text Classification (F32)
100% 689
990.1 IPS
 
Text Classification (F16)
100% 687
987.3 IPS
 
Text Classification (I8)
98% 477
685.2 IPS
 
Machine Translation (F32)
100% 1122
20.7 IPS
 
Machine Translation (F16)
100% 1116
20.5 IPS
 
Machine Translation (I8)
70% 624
11.5 IPS
 

Compare

Set Baseline Geekbench 6 now available