Geekbench ML Score

2223
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date March 05 2025 03:35 PM
Views 4

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model ASUSTeK COMPUTER INC. ROG Zephyrus G15 GA503QR_GA503QR
Motherboard ASUSTeK COMPUTER INC. GA503QR
Power PlanPerformance
CPU Information
Name AMD Ryzen 9 5900HS
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 40.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device AMD Radeon(TM) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1137
212.7 IPS
 
Image Classification (F16)
100% 1149
215.0 IPS
 
Image Classification (I8)
99% 967
180.9 IPS
 
Image Segmentation (F32)
100% 884
14.8 IPS
 
Image Segmentation (F16)
100% 888
14.8 IPS
 
Image Segmentation (I8)
98% 747
12.5 IPS
 
Pose Estimation (F32)
100% 11277
13.7 IPS
 
Pose Estimation (F16)
100% 11198
13.6 IPS
 
Pose Estimation (I8)
100% 7929
9.60 IPS
 
Object Detection (F32)
100% 871
65.0 IPS
 
Object Detection (F16)
100% 878
65.6 IPS
 
Object Detection (I8)
67% 748
55.8 IPS
 
Face Detection (F32)
100% 1437
17.1 IPS
 
Face Detection (F16)
100% 1436
17.1 IPS
 
Face Detection (I8)
89% 1109
13.2 IPS
 
Depth Estimation (F32)
100% 5132
39.8 IPS
 
Depth Estimation (F16)
100% 5008
38.8 IPS
 
Depth Estimation (I8)
94% 3784
29.3 IPS
 
Style Transfer (F32)
100% 19692
25.9 IPS
 
Style Transfer (F16)
100% 19621
25.8 IPS
 
Style Transfer (I8)
98% 12895
17.0 IPS
 
Image Super-Resolution (F32)
100% 4375
156.2 IPS
 
Image Super-Resolution (F16)
100% 4427
158.1 IPS
 
Image Super-Resolution (I8)
99% 3040
108.6 IPS
 
Text Classification (F32)
100% 981
1.41 KIPS
 
Text Classification (F16)
100% 982
1.41 KIPS
 
Text Classification (I8)
98% 668
960.0 IPS
 
Machine Translation (F32)
100% 1381
25.4 IPS
 
Machine Translation (F16)
100% 1366
25.1 IPS
 
Machine Translation (I8)
69% 766
14.1 IPS
 

Compare

Set Baseline Geekbench 6 now available