Geekbench ML Score

3147
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date September 05 2025 03:42 AM
Views 11

System Information

System Information
Operating System Microsoft Windows 11 Home Single Language (64-bit)
Model LENOVO 83HY
Motherboard LENOVO LNVNB161216
Power PlanBalanced
CPU Information
Name AMD Ryzen AI 7 350
Topology 1 Processor, 8 Cores, 16 Threads
Identifier AuthenticAMD Family 26 Model 96 Stepping 0
Base Frequency 2.00 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache32.0 KB x 8
L1 Data Cache48.0 KB x 8
L2 Cache1.00 MB x 8
L3 Cache16.0 MB x 1
Memory Information
Size 16.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device AMD Radeon(TM) 860M Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1498
280.2 IPS
 
Image Classification (F16)
100% 1472
275.5 IPS
 
Image Classification (I8)
100% 1194
223.5 IPS
 
Image Segmentation (F32)
100% 1799
30.0 IPS
 
Image Segmentation (F16)
100% 1776
29.7 IPS
 
Image Segmentation (I8)
98% 1478
24.7 IPS
 
Pose Estimation (F32)
100% 21804
26.4 IPS
 
Pose Estimation (F16)
100% 21979
26.6 IPS
 
Pose Estimation (I8)
100% 15250
18.5 IPS
 
Object Detection (F32)
100% 1205
89.9 IPS
 
Object Detection (F16)
100% 974
72.7 IPS
 
Object Detection (I8)
62% 920
68.6 IPS
 
Face Detection (F32)
100% 2829
33.6 IPS
 
Face Detection (F16)
100% 2879
34.2 IPS
 
Face Detection (I8)
89% 2180
25.9 IPS
 
Depth Estimation (F32)
100% 9304
72.2 IPS
 
Depth Estimation (F16)
100% 8855
68.7 IPS
 
Depth Estimation (I8)
95% 6406
49.7 IPS
 
Style Transfer (F32)
100% 24572
32.3 IPS
 
Style Transfer (F16)
100% 24389
32.1 IPS
 
Style Transfer (I8)
98% 19515
25.7 IPS
 
Image Super-Resolution (F32)
100% 3820
136.4 IPS
 
Image Super-Resolution (F16)
100% 3585
128.0 IPS
 
Image Super-Resolution (I8)
99% 2948
105.3 IPS
 
Text Classification (F32)
100% 737
1.06 KIPS
 
Text Classification (F16)
100% 828
1.19 KIPS
 
Text Classification (I8)
98% 1197
1.72 KIPS
 
Machine Translation (F32)
100% 1797
33.1 IPS
 
Machine Translation (F16)
100% 1670
30.7 IPS
 
Machine Translation (I8)
70% 917
16.9 IPS
 

Compare

Set Baseline Geekbench 6 now available